Server has 7 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (10-100 chars, mostly adequate), and input schemas are present with type definitions. However, naming conventions are inconsistent (e.g., 'me/playlists' violates verb_noun pattern), parameter descriptions lack detail on constraints and formats, and output schemas are not documented. Error handling exists but lacks recovery guidance. No tool annotations (readOnlyHint, etc.) despite all being read-only. Response filtering is minimal, tools return raw API data without stripping irrelevant fields.
Get information about a specific artist including name, genres, followers, popularity, and images
Get the current user's profile information including ID, name, email, images, country, and subscription type
Get the current user's playlists
Get the current user's top tracks
Get information about a specific playlist including name, owner, tracks, and total track count
Search for tracks, artists, or albums on Spotify
Get information about a specific track including name, artist, album, duration, popularity, and preview URL
Tool naming violates verb_noun convention. 'me', 'me/playlists', 'me/top/tracks' are REST paths, not action verbs. Should be 'get_current_user', 'list_user_playlists', 'list_user_top_tracks'. LLMs cannot infer intent from path-style names.
Output schemas not documented. Tools return raw Spotify API responses (e.g., artist returns name, genres, followers, popularity, images) but LLMs cannot plan downstream calls without knowing field names and types. No pagination info returned despite search accepting limit parameter.
Parameter descriptions lack constraint details. 'limit' parameter says 'Maximum number of results' but omits min/max bounds (1-50 visible in schema but not in description text). 'query' has no format guidance. LLMs cannot validate inputs without explicit descriptions.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 43 | 2026-07-28+ | v2 |
No tool annotations despite all tools being read-only. Missing readOnlyHint annotation prevents agents from understanding safety profile. No idempotentHint either, though all tools are idempotent.
Error messages lack recovery guidance. Code returns 'Resource not found' but does not suggest alternatives (e.g., 'Artist not found. Try search() with a partial name'). Agents cannot self-correct without actionable error context.