Trakt MCP has well-structured tool definitions with clear naming (verb_noun pattern) and complete input schemas. All 7 tools have descriptions and required parameters are properly marked. However, descriptions are terse (avg ~80 chars, below the 194-char baseline), parameter descriptions lack detail on constraints and formats, and output schemas are entirely undocumented. No error handling guidance, no pagination details despite list tools, and no indication of response structure. The server reads from Trakt API but does not document what fields agents should expect in responses.
Single episode by show + season + episode number.
Movie record by trakt ID / slug / IMDB ID. Use extended=full for plot/runtime/genres/cast.
Show record. Use extended=full for runtime/genres/cast/rating/airs/etc.
Seasons + episode counts for a show.
All-time popular movies or shows.
Search Trakt. type = comma-separated of movie, show, episode, person, list. Returns each result with score + matched object.
Output schemas completely undocumented. LLMs cannot plan downstream calls or extract fields without knowing response structure. No documentation of what fields search(), get_movie(), list_seasons() return.
Parameter descriptions lack actionable constraints. 'extended' param says 'full | metadata | images' but should specify: 'One of: full, metadata, images. Use full to include plot, runtime, genres, cast.' Numeric params (page, limit) lack min/max bounds.
No error handling guidance. If API returns 401 (invalid key), 404 (not found), or 429 (rate limit), LLM receives raw error with no recovery hint. Should return: 'Movie not found. Try search() with a partial title.'
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Currently-trending movies or shows.
Pagination not documented for list tools. search() and trending/popular accept page/limit but no mention of total count, next_cursor, or result cap. LLM cannot know if 10 results is all available or if more pages exist.
Tool descriptions are below baseline (avg 80 chars vs 194-char baseline). 'Seasons + episode counts for a show' lacks context on when to call it vs get_show. Should explain: 'Call this to list all seasons of a show and get episode counts per season. Use extended=episodes to include full episode details.'