A repository demonstrating code execution capabilities with MCP, including a FastAPI demo server and MCP client utilities for library documentation fetching
Both tools have minimal descriptions (under 100 chars) and lack parameter-level documentation. Input schemas are present but sparse: parameters have types (string) but no descriptions, violating the requirement that every parameter must explain what it controls. Tool names lack action verbs (resolve-library-id, query-docs are noun-heavy). No output schema is documented. Error handling is absent, no guidance on what to do if resolution fails or docs are not found. The server acts as a thin wrapper around an external Context7 service, delegating all logic, which limits the ability to provide rich error recovery or validation.
Queries documentation for a given library ID and search query
Resolves a library name and query to a Context7-compatible library ID
Parameter descriptions missing. Both tools have input parameters (libraryName, query, libraryId) with no descriptions explaining what they control or how to format them. LLMs cannot infer parameter meaning from names alone.
Tool descriptions are too brief (under 100 chars). 'Resolves a library name and query to a Context7-compatible library ID' lacks context on when to use this tool, what it returns, or what happens on failure. Descriptions should be 50-200 chars with clear intent.
No output schema documented. LLMs cannot plan downstream calls or extract data if they don't know what fields to expect. Both tools return text but structure is opaque.
Tool names lack action verbs. 'resolve-library-id' and 'query-docs' are noun-heavy and do not clearly signal what action occurs. Prefer 'get_library_id' or 'search_documentation'.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 31 | 2026-07-28+ | v2 |
No error handling or recovery guidance. If library resolution fails or docs are not found, the tool provides no actionable error message or next steps for the LLM.