Server has 6 tools with basic verb-noun naming (search_user, get_user_name, etc.). All tools have short descriptions (10-50 chars) that lack depth, they state WHAT but not WHEN to use or dependencies. Input schemas are present with type definitions but parameter descriptions are minimal (5-20 chars). No output schemas documented. Error handling is absent, tools raise ValueError with generic messages that don't guide LLM recovery. No tool annotations (readOnlyHint, etc.). Tools are read-only and well-scoped, but descriptions fall well below the 50-200 char baseline for A+ tools. Parameter descriptions like 'User ID' are too terse to guide LLM reasoning.
Get user avatar URL
Get user live status (0-not live, 1-live)
Get live room title (empty string if not live)
Get live room cover URL
Get user nickname
Search user by nickname and return uid and name
Parameter descriptions are too terse (5-20 chars). 'User ID' and 'User nickname to search for' lack context on format, constraints, or when to use each tool.
No output schemas documented. Tools return strings, ints, or dicts but LLM cannot predict structure. E.g., search_user returns {uid, name} but this is not formally declared.
Error handling is generic. ValueError exceptions with messages like 'No matching user found' or 'API Error' do not guide LLM recovery. No retry guidance, no actionable next steps.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2026-07-28+ | v2 |
Tool descriptions are 10-50 chars, well below the 50-200 char baseline. They lack context on when to call each tool vs. alternatives, dependencies, or prerequisites.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are read-only but this is not formally declared in the schema.