Read-only FirstCall-generated MCP server for looking up public API user records.
Single tool with critical definition gaps. Tool name 'github_user_lookup' lacks action verb prefix (should be 'get_github_user' or 'lookup_github_user'). Description is generic ('Verified API tool recipes for AI agents') and does not explain what the tool does, when to use it, or what it returns, fails the 10-1024 character guideline for meaningful content. Input parameter 'username' has description 'path' (3 chars), far below the 20-char minimum and provides zero context. No output schema documented in the tool registration despite returning structured ToolOutput. Tool annotations present but descriptions absent make them useless to LLMs.
Verified API tool recipes for AI agents.
Tool description is non-actionable. 'Verified API tool recipes for AI agents' does not explain what the tool does, when to call it, or what it returns. LLMs cannot determine when to select this tool.
Input parameter 'username' has description 'path' (3 characters). Fails minimum 20-char guideline. Does not explain what username is, format, or constraints. LLM cannot infer whether to pass 'octocat', '[email protected]', or a user ID.
Tool name 'github_user_lookup' does not start with action verb. Should be 'get_github_user' or 'lookup_github_user' to match verb_noun convention. Current name is ambiguous about what action occurs.
Output schema documented in code (ToolOutput type with status, ok, body_preview) but NOT registered in server.registerTool() outputSchema. LLMs cannot see what fields to expect from the response.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 30 | 2025-06-18+ | v2 |
No error handling guidance. Tool calls external GitHub API but provides no recovery hints if user not found, rate limited, or network fails. LLM has no guidance on what to do next.