A LangChain-based multi-agent system for travel booking coordination using MCP (Model Context Protocol) to integrate with Airbnb search capabilities
Three tools with mixed quality. airbnb_search_agent has a complete schema with all parameters typed and described (location, checkin, checkout, adults with defaults). However, airbnb_search and airbnb_listing_details lack visible input schemas in the source code, only names and brief descriptions are shown. Descriptions are present but minimal (10-50 chars), below the 194-char baseline. No output schemas documented. No error handling guidance. Tool composition is reasonable (search → details), but parameter descriptions lack format constraints (date format stated in airbnb_search_agent but not enforced across tools).
Get detailed information about an Airbnb listing (from MCP server)
Search for available Airbnb properties (from MCP server)
An agent that searches for available Airbnb properties.
airbnb_search and airbnb_listing_details have no visible input schemas in source code. Cannot verify parameter types, constraints, or descriptions.
No output schemas documented for any tool. LLMs cannot predict response structure or plan downstream calls.
Descriptions are too brief (10-50 chars vs 194-char baseline). airbnb_search: 'Search for available Airbnb properties (from MCP server)' lacks WHEN to use it and what it returns.
Date format constraint (DD-MM-YYYY) only documented in airbnb_search_agent schema, not in parameter descriptions for checkin/checkout. Inconsistent across tools.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 46 | 2026-07-28+ | v2 |
No error handling guidance. Tools do not indicate what to do if location is invalid, dates are in the past, or no properties are found.