Tool search 101,866 tools · 5,225 live servers

Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.

Full registry record for one wine: producer, region, appellation, classification, grapes, community rating, and the AI tasting profile when the wine has been enriched. Vintage-neutral (bottles carry the vintage). Call after search_registry when the user wants depth on a specific wine.

Given a registry wine_id (or one of the user's bottle_ids), returns wines with the closest taste/style profile from the shared registry, using vector similarity over wine embeddings. Call for "more like this", "what else is like my favourite Barolo", or to seed purchase ideas from a wine the user loves. Only wines that have been embedded are searchable — an empty result does not mean nothing similar exists.

Get comprehensive data for a stock, ETF, or crypto ticker. Returns: - ticker, name, type (e.g. 'stock', 'etf', 'crypto'), industry - latest_price, page_url - bullish_case, bearish_case, potential_outcomes, takeaway, analysis_date (AI-generated) - price_forecast_days, price_forecast_percent, price_forecast_lower/upper_bound_percent (model price forecast) - future_uncertainty_urls: dict with image URLs for future_uncertainty, term_structure, volatility_surface, return_profile (when available) - future_uncertainty_last_updated, term_structure_last_updated - iv_rank_percentile (0-100, IV rank over past year) - long_vol_call, long_vol_put, short_vol_call, short_vol_put: full option pack dicts (when available) Throws an error if the ticker is not recognized. Args: ticker: Ticker symbol, e.g. 'AAPL', 'AMZN', 'BTC', 'ETH', 'SPY'.

Get comprehensive bias analysis for a news source. Returns: - source_name, slug_name, page_url - source_match: original query and deterministic match method - articles_analyzed: total articles in the bias database for this source - last_updated: source-profile aggregation timestamp - avg_social_shares: average social shares per article - emotionality_score (0-10): how emotional the writing is - prescriptiveness_score (0-10): how much the source tells readers what to think/do - bias_values: canonical plain-text source-level weighted display scores (-50 to +50 bipolar, 0 to +50 unipolar). Keys match the article tools; these are directional source summaries, not raw article-score averages. - bias_scores: legacy emoji-prefixed display scores - bias_score_methodology: scope and evidence caveats for aggregate scores - bias_description: clean-text, AI-generated overall bias summary narrative - bias_description_metadata: generation time, automated review status, and evidence scope - bias_description_html: optional website HTML when include_html=true - liberal_conservative_description: narrative on political leaning - libertarian_authoritarian_description: narrative on authority stance - signature_phrases: words/phrases uniquely overrepresented vs other sources - signature_negative_phrases: uniquely negative/alarming phrases - most_shared_phrases: phrases in their most viral articles - most_emotional_phrases: phrases used in their most emotional articles - pays_for_traffic_keywords: keywords this source buys ads for - similar_sources: sources with the most similar bias profile - most_different_sources: sources with the most different bias profile - trends_graph_url: URL to a chart of this source's coverage volume over time - bias_plot_urls: dict of 2D bias scatter plot image URLs (political_lib_auth, subjective_objective, informative_opinion, oversimplification_factful) — only present when available - recent_articles: list of most recent articles with full article fields, bias_values, analysis status, and optional self-contained bias_dimensions and bias_analysis. Evidence quotes include verification method and exact character offsets when available. - recent_evidence_coverage: reconciled counts for verified, unverified, partial, legacy-scored, and pending articles, plus evidence-bearing count and verified ratio Throws an error if the source is not found. Args: source: Source name, slug, or domain (e.g. 'Fox', 'reuters', 'bbc.co.uk'). Partial names are accepted only when they identify one source; ambiguous input returns candidates. recent_articles: Number of recent articles to include (1-50, default 10). include_evidence: Include per-article claims, verbatim evidence, counterevidence, confidence, rationale, and limitations. Defaults to false to keep multi-article source payloads compact. include_html: Also return the original website-formatted source narrative. Defaults to false.

Book a hotel room using a rate from get_hotel_details. Requires a Gondola account (API key) and a saved payment method. Use get_payment_methods to find your payment ID. The gondola_rate_id comes from the room rates returned by get_hotel_details — each room option has a rate ID you can use here. Guest details (given_name, family_name, email_address, phone_number) can either be passed directly or prefilled from a saved travel profile: pass travel_profile_id (from get_travel_profiles) to book "as <traveler>" without collecting each field. Any field you also pass explicitly overrides the profile. To earn points and elite credit, pass loyalty_account_id — use the Member Number from get_loyalty_accounts that matches the hotel's chain (e.g. the World of Hyatt account for a Hyatt property). When a loyalty_account_id is passed, the booking goes out under the email registered to that membership (overriding any travel profile or email_address), so the stay credits to the right account. Args: gondola_rate_id: The rate ID from get_hotel_details room rates. payment_id: Payment method ID from get_payment_methods. given_name: Guest's first name (optional if travel_profile_id is provided). family_name: Guest's last name (optional if travel_profile_id is provided). email_address: Guest's email for confirmation (optional if travel_profile_id is provided). phone_number: Guest's phone number with country code (optional if travel_profile_id is provided). special_request: Optional special request for the hotel (e.g. "high floor", "late check-in"). loyalty_account_id: Optional Member Number (from get_loyalty_accounts) to earn points. travel_profile_id: Optional travel profile ID (from get_travel_profiles) to prefill guest details. Returns: Booking confirmation with ID and details, or an error message.

Analyze the user's whole loyalty portfolio and surface the highest-value actions. Trip-independent. Looks across every loyalty program the user holds — plus the transferable card currencies (Amex, Chase, Bilt, etc.) that can feed hotel programs — and reports points expiring soon (ranked by value at risk), the best transfer opportunities, and the largest balances. When the user's travel profile is available, it also tailors the view to their home airport, the airlines they fly, their frequent destinations, and when they travel (e.g. flagging points that expire before their usual travel months). Takes no arguments. Use this when the user asks how to make the most of their points, what's expiring, or where they can transfer. For deciding where to book a specific trip, use search_hotels / compare_rates instead. Returns: A Markdown portfolio summary, or instructions to connect accounts when none are linked.

Get the user's saved travel profiles (guest name, email, and phone presets). Each profile has a selectable Profile ID. Pass it to book_hotel as `travel_profile_id` to prefill the guest details — the same "book as <traveler>" selection the website checkout offers — instead of collecting name, email, and phone field by field. Requires a Gondola account (API key). Returns: Formatted list of travel profiles with IDs, or instructions to add one.

Save a learned travel preference or experience to the user's traveler profile. Use when the user shares a durable preference, like, dislike, or trip experience that should inform future recommendations — "Always takes a window seat", "Prefers boutique hotels over chains", "Vegetarian". Don't save temporary logistics like "my flight lands at 3pm". Saved entries come back from get_traveler_context in later sessions, which is how a preference stated once is still known next time. Requires a Gondola account (API key). Args: profile_entry: The preference or experience to save. Be specific and actionable. Good: "Prefers ocean-view rooms". Bad: "Liked the hotel". Returns: Confirmation of the saved entry, or an error message.

Nearest RAOB (radiosonde) vertical soundings to a point. Each sounding carries: profile (pressure-indexed thermodynamics: pressure_hpa, height_m, temperature_c, dewpoint_c, wind arrays), wind_profile (height-indexed winds for hodographs/shear), and derived indices (sbcape/mucape/mlcape + cin, lifted_index, k_index, total_totals, pwat_mm, freezing_level_m, lcl/lfc/el, bulk_shear_0_6km_kt). Soundings launch at 00Z/12Z so data can be hours old. Example: {"location": "Norman, OK"}.

Render the nearest RAOB (radiosonde) sounding as a Skew-T log-P + hodograph chart image for visual analysis: temperature/dewpoint traces, wind barbs, height-banded hodograph, and a derived-indices table (CAPE/CIN, lifted index, PWAT, shear, LCL). Soundings launch at 00Z/12Z so data can be hours old. Use get_sounding for the raw profile numbers. Example: {"location": "Norman, OK"}.

[Public] Register a new agent. Returns API key, wallet with deposit address and required amount immediately. Email verification is optional but required to access user profiles.

[Auth Required + Active] Get user profile by ID (paid action: api_user_view after free limit). Requires active account (deposit verified). Pass API key via X-Agent-Key header or Authorization: Bearer.

[Auth Required] Get the authenticated agent's profile information. Pass API key via X-Agent-Key header or Authorization: Bearer.

[Auth Required] Update the authenticated agent's profile. Pass API key via X-Agent-Key header or Authorization: Bearer.

[Auth Required] List browsers where you have pre-arranged rent contracts (free/discount, main_profile access, allowed_domains override). Returns array of browsers with resolved price. Call this before deciding which browser to rent — you may have free or discounted access.

[Auth Required + Active] Get credentials to rent a real Chrome browser. Install CLI: `pip install ceki-sdk` (Python) or `npm install -g @ceki/sdk` (Node). Usage: `ceki rent --schedule ID` → session_id, then `ceki navigate SID URL`, `ceki screenshot SID -o file.png`, `ceki stop SID`. Per-minute billing from AgentWallet. For captcha-protected signups, call `pre-warm-captcha-protected-site` prompt first. Rate limit: 20 rents/hour per agent (production); on `429 Rate limit exceeded` respect the `Retry-After` header (seconds until the next UTC-hour bucket) before retrying.

"Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO, news, GLEIF and returns: cik + company_name; recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. Pass ticker "AAPL" or zero-padded CIK "0000320193" — names not supported (use resolve_entity first if you only have a name).

"What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).

Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.

List files in the file library (images/attachments). KnowledgeOwl API: GET /file.json. Returns { valid, page_stats, data:[...] }.

Search the 12,338 curated, SAMHSA-sourced US addiction treatment facility directory by state, city, treatment type, and insurance. Returns matched facilities with name, city/state, programs offered, insurance accepted, phone, and browse URL. Use this to find candidates — then call get_facility_detail for one facility's full profile. If the user is uncertain about location coverage, call list_states first.

Get the full profile of one specific treatment facility: address, phone, programs offered, insurance plans accepted, SAMHSA verification status, and a direct browse URL. Supports partial name matching — returns the best match if multiple facilities contain the query string. Use after search_facilities when the user wants to drill into a named facility.

List the files attached to a document. Returns `[{file_uid, file_name, kind, pages_count, published_at}]` — each entry's `file_uid` can be passed to `download_document_file`. A document often has several PDFs (e.g. cleaned + original); use this tool to enumerate them and pick the right one before download.

Issue a personal URL to download the document PDF from hpt.su. Returns `{download_url, file_name, kind, document_id}`. The link is personal: opening it works only when signed in to hpt.su under the same account that owns the API key. The download quota is charged at actual download time, not when the link is issued. Requires an active subscription covering the document's kind or a one-time purchase of this document. On the free tier returns 403 with an upgrade prompt to https://hpt.su/pricing/.

Read a future adoption profile without inventing unavailable data.

Get details about one agency or developer by id or slug (from search_companies): profile, rating, specialties, languages, service areas, and contact info.

Get details about one real estate agent by id or slug: profile, rating, reviews, specialties, and contact info.

Search REGISTERED real-estate agents and professionals on Tu Lugar by name, city, or company. Only covers people who created a public profile on the platform — there is no data about anyone else.

Re-hosts an image so its URL is suitable for the `images` array of a HighlightStory. Pass `url` (recommended; server fetches + stores) or `data_url` (small files only, RFC 2397 inline base64). Storage is content-addressed at floor10/highlights/<member_id>/<sha256>.<ext> on Vercel Blob, public-readable, year-long cache. Idempotent: same bytes -> same URL. Rate limit: 30 uploads / token / UTC day (separate from the submission rate). Allowed types: image/jpeg|png|webp|gif|heic|heif|avif. Max 8 MB per upload. Returns: { url, bytes, content_type, sha256, deduped }.

The ACTUAL account roster — every Clerk-backed IC account with its live ring/tier, resolved from Clerk (not the carded ic_directory_search, which only shows members who've set a profile card, and not the curated kiosk list). This is what you want to answer 'who are the members' or find a specific account (e.g. one that hasn't set a card yet). Each member: { user_id, name, email, tier ('public'|'ft-member'|'ai-floor'|'ic-member'|'operator'), pending_request (the tier they've requested but not yet been granted, or null), created_at }. Args: { tier?: filter to one ring; q?: case-insensitive name/email/user_id substring filter; limit?: number (default 200, max 500); offset?: number (default 0) }. Filters apply to the fetched page; `total` is the full Clerk account count and `has_more` tells you to page with offset (default limit covers all IC accounts in one page today). Required scope: admin:tier_review.

Retrieve the 5-hour Z.ai Claude-Code key you filed with ic_request_workshop_key, once an IC operator has approved it. Poll with the request_id that ic_request_workshop_key returned. While the operator hasn't approved yet returns { ok:true, status:'pending' } (keep polling). On the FIRST call after approval returns { ok:true, status:'ready', agent_token, bundle } where bundle.copy_paste is the paste-and-go Claude Code setup block. The key is surfaced EXACTLY ONCE and the pickup window is ~15 min after approval, so call again promptly once approved. A second pickup, a lapsed window, or a denied/unknown request returns a terminal status with what to do next. You can only retrieve your OWN request. Args: { request_id }. Required scope: keys:request.

Retrieve the weekly-token Z.ai Claude-Code key you filed with ic_request_zai_key, once an IC operator has approved it. An agent-inbox notification announces approval; this tool is the actual pickup. Poll with the request_id that ic_request_zai_key returned. While unapproved returns { ok:true, status:'pending' } (keep polling). On the FIRST call after approval returns { ok:true, status:'ready', agent_token, bundle } where bundle.copy_paste is the paste-and-go Claude Code setup block. The key is surfaced EXACTLY ONCE and the pickup window is ~15 min after approval, so pick it up promptly. The key itself does not expire (weekly token budget, resets Monday). A second pickup, a lapsed window, or a denied/unknown request returns a terminal status. You can only retrieve your OWN request. Args: { request_id }. Required scope: keys:request.

Report the weekly token usage + remaining budget for the member (weekly-token) Z.ai Claude-Code key you filed with ic_request_zai_key. Poll with the request_id ic_request_zai_key returned (after an operator approved it). Returns { ok:true, weekly_used, weekly_remaining, weekly_cap, multiplier, reset_date } where weekly_used = input+output tokens metered by the IC->Z.ai gateway this week, weekly_cap = base × multiplier, and reset_date is the next Monday (UTC) when the meter rolls over. weekly_used fails soft to 0 if no calls were metered yet or the meter is briefly unreadable. Workshop (5-hour) keys are time-boxed and have NO weekly budget — this returns ok:false for them (check expiry, not usage). You can only read your OWN request. Args: { request_id }. Required scope: keys:request.

Edit the calling user's public-facing profile fields: first name, opt-in visibility, and company website. Company logo is auto-derived from the website at save time (Clearbit + favicon fallback). Re-posting overwrites. Opt-in members are listed publicly on /members and the kiosk; opted-out members are visible to directory:search callers only at their ring or below. Args: { first_name?: string, company_website?: string, public_visible?: boolean }. Returns: { ok, profile }. Required scope: membership:write.

Search advertisers, game studios, or mobile games by name and optional genre, region, and platform filters. Use the returned advertiser_id with get_advertiser_profile. Example: 'Find the advertiser for Last War.'

Get an advertiser or game profile, including recent ad activity, creative volume, target countries, and platforms. Creative tag fields are normalized to English in the result. Example: 'Which markets and platforms is this game scaling on?'

Find the single best-matching person profile for a set of identifying attributes (name, email, phone, profile URL, company, etc.). Returns one record plus a likelihood score (1-10), or a 404 'no match' body. Use uniquely-identifying inputs for best results. API: GET /person/enrich.

Given broad, possibly-ambiguous attributes about a person, return up to 20 strongly-related profiles ranked by match score. Sits between enrich (1:1) and search (open-ended) — ideal when you can't uniquely resolve someone. API: GET /person/identify.

Search the full PDL Person Dataset with an Elasticsearch query object OR a SQL string over the Person Schema (e.g. everyone with job_title_role='engineering' at a company). Returns matching profiles sorted by completeness; paginate with scroll_token. Each returned record costs 1 credit. API: POST /person/search.

Find the single best-matching company record. Requires a non-ambiguous input — name OR website OR ticker OR profile (website/ticker/profile resolve more reliably than name). Returns firmographics (industry, size, location, etc.) or a 404 'no match' body. API: GET /company/enrich.

Full profile of one journal by ISSN: indexing, quartile, trust score with breakdown, APC, open-access status, scope, and integrity signals (e.g. DOAJ withdrawal). Use when the user asks about a specific journal.

Search CreateMod.com for Minecraft Create Mod schematics. Returns matching builds with title, page URL, rating and stats. Send users to the page URL; never fetch .nbt schematic files.

Get details about one schematic by its URL slug: description, author, rating, versions, required mods, video. The schematic file itself is not available to agents; direct users to the page URL.

Download a job's results as a CSV file. Use when: - You want the full job output as a CSV for offline analysis or export. - Prefer this over `pull_results` when the consumer needs spreadsheet/CSV format.

Download the latest monitor run's results as a CSV file. Use when: - You want the most recent monitor run output as a CSV for offline analysis or export. - Prefer this over `pull_monitor_results` when the consumer needs spreadsheet/CSV format.

Create a new dataset by uploading a CSV file. The CSV must have at least a `name` column. For meaningful entity enrichment each row should also include a `domain` column or a `description` column (or both) — a row with only a name is accepted but produces lower-quality enrichment. Additional columns are mapped to entity attributes. Max file size is plan-dependent. To add CSV rows to an existing dataset, use `append_csv_to_dataset` instead.

Append entities from a CSV file to an existing dataset. Parses the CSV and appends its entities to the dataset. Each row must have a `name` column; include a `domain` or `description` column (or both) for meaningful enrichment. Duplicate rows (by name) are skipped. To create a new dataset from a CSV, use `create_dataset_from_csv` instead.

Check the current user's account status: API call balance, plan, enabled/disabled graphs, and profile info. Use when the user asks "how many API calls do I have?", "what plan am I on?", "what graphs can I access?", or similar account questions. Returns live data — not cached from session start.

Get the full profile of a specific trend — detailed description, lifecycle stage (emerging/building/mature), signal strength, geographic scope, and all properties. Use when you need deeper detail on a single trend after search_graph returned a summary. Requires node_id from a prior search_graph result.

Get full details for a specific piece set including manifest, piece file list, direct SVG URLs, and a preview image URL. Use piece_gallery_search to find set IDs first.

Find BeachFinder water and coastal activity providers for lessons, rentals, equipment, repair needs, guided trips, clubs, campsites and excursions. Results state whether each profile is owner verified, source backed or mapped, and return only name, category, approximate location and BeachFinder profile link.

Register an agent/collective into the match index (mission + domain profile + constitutional alignment scores + capacity).

Get a contributor's public profile and their published listings, by contributor slug (not a listing slug). Read-only, no authentication required (public endpoint, IP rate-limited). Returns display_name, bio, credential_summary, positioning_statement, badge_tier, avg_rating, review_count, pull_quote, social/website URLs, credential_badges, published_listing_count, and a listings array (slug, title, price_cents) for that contributor. Use to learn more about who built a listing returned by search or fetch -- not for looking up a listing directly.

Return the current workspace document (ops log + cursor + meta) plus the materialized mapPlan and layerFilters, in a shape suitable for save-to-file / share-by-URL / inspection. Pure read — no mutation, no credit charge. Use this when you want the full raw state for serialization; use get_state when you want the compact envelope for display.

Export a single layer's features as a downloadable file. Returns a URL with Content-Disposition: attachment so the user's browser downloads it. CSV drops geometry beyond a (lng, lat) centroid — for full polygon/line geometry, use format: "geojson". The URL is an unguessable capability link that does NOT expire — treat it as shareable-forever, not temporary. Required: map_id, layer_id, format, rationale.

Returns a deep-link URL that opens the map in the user's browser and automatically triggers a PNG download. The user clicks the link, the browser renders the map at full resolution with the legend composited (if legend: true), and the file downloads. There is no server-side rendering; the user's browser is the renderer. Required: map_id, rationale. Optional: format (png default), legend (true default).

Tell the ShowMeOnMap team your agent hit something it could not accomplish — an unsupported intent, a missing tool, an unclear schema, an op that failed in a confusing way. Use this when build_map / mutate_map / a direct-op tool returns something you cannot recover from, OR when you would have wanted a different tool to exist. Records the report to a server-side log; does not unblock the current session, but feeds future capability work. No map_id required — file the report even if no map was built.

Your revenue-share balance: contributors receive a quarterly portion of net advertising revenue, allocated by article readership + reputation points. Shows payable/carried/paid amounts and whether payout details are on file. Contributor Revenue Share Terms: (1) Each quarter, The Data Commenter's administrators may, at their sole discretion, designate a portion of net advertising revenue (after expenses) as the contributor pool; the pool may be zero. (2) The pool is allocated proportionally to each contributor's quarterly score: views on their published community articles plus reputation points earned that quarter (1 point = 25 view-equivalents). Bot and crawler traffic is excluded. (3) Balances under $10 roll into the following quarter. (4) Payouts require valid payout details; balances unclaimed 12 months after becoming payable may be forfeited. (5) Amounts are gratuitous revenue sharing, not wages, royalties, or an employment/partnership relationship; you are responsible for your own taxes. (6) Fraud, artificial traffic, plagiarism, or terms violations disqualify earnings. (7) The program may be modified or discontinued prospectively at any time.

Computes the aggregate entropy-calibrated alpha for a corpus without running a full search -- useful to inspect before committing to a large rank_items_by_nmi_cosine_fusion call. Returns a single aggregate corpus_entropy value, NOT a per-dimension breakdown -- the real logic only exposes the mean marginal entropy across dimensions, not H(X_d) per individual dimension. Do NOT use expecting per-dimension granularity. Requires a valid api_key (same as X-API-Key) and an x402 payment.

Fetch a single Romanian company by CUI (accepts an 'RO' prefix): identity, address, CAEN activities, latest public financials, and data-source freshness. Does not return contact details.

Wohnungs-Chancen-Check for Swiss tenants: rates chances on the rental market (tenant score 0–100) from a search profile using real BFS vacancy, rent and ZKB market data, and suggests better alternative regions. Use for "how are my chances of finding a 3.5-room flat in Zürich for 2200". Afterwards the tenant can register in the pool via join_tenant_pool.

Register a Swiss tenant in the Immoswipe Mieter-Pool so property managers see their search profile and contact them about matching units. WRITE operation with personal data: ONLY call after the user has EXPLICITLY agreed to join the pool. consent must be true. Typical flow: run check_rental_chances first, then offer the sign-up.

Find real local businesses in Mexico and Latin America by location, vertical, and capabilities. USE WHEN: - User asks for a service: "find me a dentist", "best restaurant", "tour in Cabo" - Location-based queries: "near me", "in Tijuana", "Cancun area" - Comparing multiple options: "top 3 dentists", "best rated hotels" - Travel planning: "things to do in Merida", "where to eat in CDMX" - Medical tourism: "affordable dental work near the border" DO NOT USE WHEN: - User asks about a specific named business (use get_business instead) - User needs contact info for a known business (use contact_business) - User asks what types of businesses are available (use list_verticals) RETURNS: List of businesses sorted by trust_score + rating. Each result includes name, city, rating, vertical, trust_score, profile_completeness, and actionable capabilities with WhatsApp deep links. If no results, returns a message with alternative cities for that vertical. BEST PRACTICES: - Always include vertical for better results - Use city name in Spanish: "Ciudad de Mexico" not "Mexico City" - Combine vertical + city for best precision - The registry spans Mexico and Latin America: by default the search covers EVERY country it holds. Pass `country` (ISO 3166-1 alpha-2, e.g. 'MX', 'CO') only to restrict it on purpose. - Results include capabilities with action_urls — pass these directly to the user for booking/contact EXAMPLES: - "dentist in Tijuana" -> vertical=dental, city=Tijuana - "restaurants in Cancun" -> vertical=restaurant, city=Cancún - "spa near Cabo" -> vertical=wellness, city=Cabo San Lucas - "hotel in Medellin Colombia" -> vertical=hospitality, city=Medellín

Retrieve the complete profile of a specific business by its slug. USE WHEN: - You already know the business slug from a previous search result - User asks for details about a specific business: hours, services, prices, contact info - You need the full profile including services, specialties, description, and all capabilities with action URLs DO NOT USE WHEN: - You don't know the slug (use search_businesses first to find it) - You only need contact info (use contact_business — lighter response) - You need to compare multiple businesses (use search_businesses) RETURNS: Complete business profile with all fields: name, description, hours, services with prices, specialties, capabilities with action_urls, trust_score, profile_completeness, languages, payment_methods, insurance_accepted, social_media, areas_served, agent_instructions, and faqs (owner-approved question/answer pairs — authoritative answers to common questions about this business). BEST PRACTICES: - The slug comes from search_businesses results (field: slug) - agent_instructions contains business-owner notes for agents — follow these when presenting the business - capabilities have action_type (whatsapp/phone/url/email) and action_url ready to use — pass directly to user - profile_completeness > 70% means reliable, complete data EXAMPLES: - get_business(slug="harmony-dental-studio-tijuana") - get_business(slug="cabo-nature-cabo-san-lucas")

Get opening hours for a specific business by day of the week. USE WHEN: - User asks "are they open right now?", "what time do they close?" - User needs to know hours for a specific day: "open on Sunday?" - Planning a visit and needs schedule info DO NOT USE WHEN: - You already have hours from get_business (it includes them) - You need more than just hours (use get_business for full profile) RETURNS: Opening hours organized by day, with open/close times. Includes today's hours highlighted. BEST PRACTICES: - If you already called get_business, hours are included — don't call this separately - Hours are in 24h format (09:00-18:00) - Some businesses have different weekend hours EXAMPLES: - get_business_hours(slug="california-s-dental-clinic-tijuana") - get_business_hours(slug="cabo-nature-cabo-san-lucas", day="sunday")

Get the list of services offered by a business, with prices and duration when available. USE WHEN: - User asks "how much does X cost?", "what services do they offer?" - Comparing prices between businesses - User needs to know duration of a service DO NOT USE WHEN: - You already have services from get_business (it includes them) - You need more than just services (use get_business for full profile) RETURNS: List of services with name, price (in local currency), and duration_minutes when available. BEST PRACTICES: - If you already called get_business, services are included — don't call this separately - Prices are in the local currency (usually MXN or USD) - Not all businesses have prices listed — recommend contacting for a quote if prices are missing EXAMPLES: - get_business_services(slug="harmony-dental-studio-tijuana")

Get the owner-approved FAQs (frequently asked questions with answers) for a business. USE WHEN: - User asks a specific question about a business that an FAQ might answer ("do they take walk-ins?", "is parking available?", "do they speak English?") - You want authoritative, business-approved answers rather than inferring from other fields - User asks "what do people usually ask about this place?" DO NOT USE WHEN: - You already have faqs from get_business (it includes them) - The business has no FAQs (the answer will be an empty list — fall back to get_business fields) RETURNS: List of FAQs, each with question and answer (in the business's language). These are written/approved by the business owner and grounded in real ficha data — safe to quote directly. BEST PRACTICES: - If you already called get_business, faqs are included — don't call this separately - Quote the answer directly; it's the owner's authoritative wording - If the list is empty, the business hasn't published FAQs yet — use other profile fields EXAMPLES: - get_business_faqs(slug="clinica-dental-costa-azul-cabo-san-lucas")

Author profile + their audiobook works. Returns biography, photo, country, and the full list of audiobook editions where this person is credited as author / co-author / editor.

Narrator profile + audiobooks they have read. Czech audiobook listeners often choose by narrator (performance quality often matters more than the underlying text).

Publisher (nakladatelství) profile + their audiobooks. Czech audiobook production is concentrated in a few publishers (Tympanum, OneHotBook, Témbr, Radioservis…); this resolves a publisher slug to its display name, audiobook count, and the list of audiobook works.