Find clusters of related learnings that are ripe for compression. When many similar solutions get linked together (e.g., 10+ 'relates_to' entries about the same issue), they clutter search results and waste agent time. Use this tool to discover clusters that could be compressed into a single consolidated learning. WORKFLOW: 1. Call get_compression_candidates with min_cluster_size=3 (or higher) 2. Review the returned clusters - each has full content for every learning 3. Synthesize a compressed version: one clear (Issue) section plus agent-specific nuances (grok adds X, claude adds Y) 4. Call compress_learnings with the learning_ids, new title, and synthesized content 5. Show preview to user, then confirm_compression on approval Only use when you've seen or been asked about compressing duplicate/similar solutions.

Get detailed information about a specific job listing/posting by its job listing ID (not application ID). Use this to view the full job posting details including description, salary, skills, and company info. For job application details, use get_application instead.

Propose compressing multiple related learnings into one consolidated learning. Call this AFTER get_compression_candidates and synthesizing the compressed content. Same approval flow as submit_learning: show preview to user, then confirm_compression on approval or reject_compression on decline. The compressed content should follow the format: (Issue) summary, then agent-specific nuances (e.g. grok adds X, claude adds Y).

Get full details for a single broker (agent) by their profile slug. Call this when the user asks for more information about a specific broker. Use the slug from search_brokers results.

Returns information about the supplier network: available destinations, experience categories, booking platforms, and protocol details. Call this before search_slots to understand what regions and activity types are available.

Returns information about the supplier network: available destinations, experience categories, booking platforms, and protocol details. Call this before search_slots to understand what regions and activity types are available.

Returns information about the supplier network: available destinations, experience categories, booking platforms, and protocol details. Call this before search_slots to understand what regions and activity types are available.

Returns structured information about what the Recursive platform includes: features, AI model details, supported integrations, and what's included at every tier. Use for systematic feature comparison.

Get full details for a single business (listing) by its slug. Call this when the user asks for more information about a specific business. Use the slug from search_businesses results.

List chats (individual AI responses) for a project over a date range. Each chat is produced by running one prompt against one AI engine on a given date. Filters: - brand_id: only chats that mentioned the given brand - prompt_id: only chats produced by the given prompt - model_id: only chats from the given AI engine (chatgpt-scraper, gpt-4o, gpt-4o-search, gpt-3.5-turbo, llama-sonar, perplexity-scraper, sonar, gemini-2.5-flash, gemini-scraper, google-ai-overview-scraper, google-ai-mode-scraper, llama-3.3-70b-instruct, deepseek-r1, claude-3.5-haiku, claude-haiku-4.5, claude-sonnet-4, grok-scraper, microsoft-copilot-scraper, grok-4) Use the returned chat IDs with get_chat to retrieve full message content, sources, and brand mentions. Returns columnar JSON: {columns, rows, rowCount}. Columns: id, prompt_id, model_id, date.

Query the DezignWorks knowledge base for information about the product, troubleshooting, features, workflows, supported hardware, and licensing. DezignWorks is reverse engineering software that integrates with SolidWorks and Autodesk Inventor, converting 3D scan data and probe measurements into parametric CAD models. Use this tool when answering questions about the product's capabilities, compatibility, or how to accomplish specific tasks.

Get full details for a single business (listing) by its slug. Call this when the user asks for more information about a specific business. Use the slug from search_businesses results.

Get full details for a single broker (agent) by their profile slug. Call this when the user asks for more information about a specific broker. Use the slug from search_brokers results.

Returns information about the supplier network: available destinations, experience categories, booking platforms, and protocol details. Call this before search_slots to understand what regions and activity types are available.

IMPORTANT: Always use this tool FIRST before working with Vaadin. Returns a comprehensive primer document with current (2025+) information about modern Vaadin development. This addresses common AI misconceptions about Vaadin and provides up-to-date information about Java vs React development models, project structure, components, and best practices. Essential reading to avoid outdated assumptions. For legacy versions (7, 8, 14), returns guidance on version-specific resources.

Get basic information about a Compute Engine Commitment, including its name, ID, status, plan, type, resources, and creation, start and end timestamps. Requires project, region, and commitment name as input.

Get basic information about a Compute Engine instance template, including its name, ID, description, machine type, region, and creation timestamp. Requires project and instance template name as input.

Get detailed information about a specific FEMA disaster declaration. Returns comprehensive data for a single disaster including all declared programs, incident dates, and affected areas. Use disaster numbers from get_disaster_declarations results. Args: disaster_number: The FEMA disaster number (e.g. 4737, 3604).

Retrieve detailed information about a specific U.S. member of Congress by their Bioguide ID (e.g., "P000197" for Nancy Pelosi).

Animate a still image into video with text guidance. Uses Grok Imagine Video — preserves source image fidelity while generating natural motion and camera movement. Async — returns requestId, poll with check_job_status. 100 sats/sec, duration 3-15 seconds. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='animate_image'.

Get basic information about a Compute Engine VM instance, including its name, ID, status, machine type, creation timestamp, and attached guest accelerators. Requires project, zone, and instance name as input.

Get information about the authenticated agent, including type, spending limits, approved categories, and configuration. Requires authentication — call 'authenticate' with your sk_buy_* key first.

Retrieve full details for a single project, including the associated client name and contact information. Use this tool when a freelancer asks about a specific project's status, budget, or timeline.

Get detailed information about a specific product by its handle (URL slug) or ID. Returns full product details including all variants, images, and availability.

Get detailed information about a specific entity by UEN. If you only have a company name, call search_entities first to obtain the UEN, then call this tool.

Get information about Syenite — the DeFi interface for AI agents. Swap/bridge routing, yield and lending, prediction markets, strategy search, alerts, wallet/gas, and trust-layer verification before signing. Call this tool to learn what tools are available and how to use them.

Get information about a published website including its title, view count, size, expiry date, and whether it has been claimed. No authentication required — this is public information. Use this to check if a site is still live, see how many views it has gotten, or check when it expires.

Retrieve detailed information about a specific story bundle by its ID, including the full timeline of related events.

Get detailed information about a specific match, including compatibility grade, strengths, concerns, and — if both parties accepted — the counterparty's contact information.

Searches the official Vonage developer documentation for guides, tutorials, and API references. This is the primary tool for general queries about Vonage's products, services, and APIs, and should be used when the user asks for information, documentation, or how-to guides.

Get information about a published website including its title, view count, size, expiry date, and whether it has been claimed. No authentication required — this is public information. Use this to check if a site is still live, see how many views it has gotten, or check when it expires.

Get detailed information about a single organization including accounts, tags, sources, products, aliases, and a short preview of its AI-generated overview when one exists. Use `get_organization_overview` to read the full overview text.

Get information about the currently active DanNet server. Returns: Dict with current server information: - server_url: The base URL of the current DanNet server - server_type: "local", "remote", or "custom" - status: Connection status information Example: info = get_current_dannet_server() # Returns: {"server_url": "https://wordnet.dk", "server_type": "remote", "status": "active"}

Get detailed information about a specific entity by UEN. If you only have a company name, call search_entities first to obtain the UEN, then call this tool.

Manually create a structured fact about a subject. Use this when the human explicitly shares personal information.

Get comprehensive information about the SAVOR Dish platform. Returns features, pricing tiers, supported platforms, and Instacart integration details. TRIGGERS: - 'what is SAVOR Dish', 'tell me about this app', 'platform info' - 'what features do you have', 'pricing plans', 'how much does it cost' - 'what platforms are supported', 'do you have a mobile app'

Get detailed information about an O*NET occupation. Returns comprehensive data including description, skills, knowledge areas, abilities, work activities, technology skills, and education requirements. Args: soc_code: The O*NET-SOC code (e.g. '15-1252.00' for Software Developers, '29-1141.00' for Registered Nurses).

Get basic information about a Compute Engine disk, including its name, ID, description, creation timestamp, size, type, status, last attach timestamp, and last detach timestamp. Requires project, zone, and disk name as input.

Retrieve detailed information about a specific U.S. federal policy by its ID (e.g., "bill-119-hr-22" or "eo-2025-1234").

Retrieve detailed information about a specific user in Teamwork Desk by their ID. Useful for auditing user records, troubleshooting ticket assignments, or integrating Desk user data into automation workflows.

Get basic information about a Compute Engine VM instance, including its name, ID, status, machine type, creation timestamp, and attached guest accelerators. Requires project, zone, and instance name as input.

Retrieves information about a specific Vonage SDK, including installation instructions, supported features, and version numbers. This is for queries focused on the SDKs themselves, not the underlying APIs.

Get full details for a specific property by ID. Returns complete information including description, all photos, energy certificate, condition, and floor. Use after search_properties to show detailed info about a property.

Retrieve detailed information about a specific ticket type in Teamwork Desk by its ID. Useful for auditing type usage, troubleshooting ticket categorization, or integrating Desk type data into automation workflows.

Get detailed information about a specific property verification mission by its ID. Returns mission details including property address, bounty amount, status, checklist items, and viewer/scout information.

Get detailed information about a specific job by its ID, including employer, agent, payout, status, validation state, and metadata URIs

Get basic information about a Compute Engine Commitment, including its name, ID, status, plan, type, resources, and creation, start and end timestamps. Requires project, region, and commitment name as input.

Get basic information about a Compute Engine disk, including its name, ID, description, creation timestamp, size, type, status, last attach timestamp, and last detach timestamp. Requires project, zone, and disk name as input.

Retrieve detailed information about a specific ticket in Teamwork Desk by its ID. Useful for auditing ticket records, troubleshooting support workflows, or integrating Desk ticket data into automation and reporting systems.

Retrieve detailed information about a specific customer in Teamwork Desk by their ID. Useful for auditing customer records, troubleshooting ticket associations, or integrating Desk customer data into automation workflows.

Get detailed information about an airport by its IATA code (e.g. "JFK", "LHR", "NRT"). Returns name, city, country, coordinates, altitude, and timezone.