Vimeo public video/user/channel/category lookups. Free personal token.
This server has critical gaps in definition quality. All 9 tools lack parameter descriptions, a hard requirement per the rubric. Tool descriptions are extremely terse (6-20 chars), violating the 10-1024 char guideline and failing to explain WHEN to use each tool or WHAT it returns. No output schemas are documented. Parameter naming is inconsistent (user_id vs channel_id_or_slug). The server exposes API key handling via _apiKey parameter, violating secret injection patterns. Error messages are generic ('Vimeo: 401'). No pagination guidance despite tools accepting page/per_page params. Naming lacks action verbs, 'video' should be 'get_video', 'videos_search' should be 'search_videos'.
List categories.
Single category.
Videos in a category.
Channel.
Channel videos.
User profile.
User videos.
All 9 tools lack parameter descriptions. The rubric requires every parameter to have a non-empty description explaining what it controls. E.g., 'id', 'query', 'user_id', 'slug' have no descriptions in the schema. LLMs cannot infer parameter meaning from names alone.
Tool descriptions are extremely terse (6-20 characters). Rubric requires 10-1024 chars and descriptions must answer WHAT the tool does, WHEN to use it, and WHAT it returns. E.g., 'Single video.' and 'Search videos.' lack context for LLM selection and do not explain return structure.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 33 | 2026-07-28+ | v2 |
Single video.
Search videos.
No output schemas documented. Rubric requires documenting return types so LLMs know what fields to expect and can plan downstream tool calls. No indication of pagination structure, field names, or data types returned by any tool.
API key exposed as _apiKey parameter in callTool args. Rubric forbids credentials as tool parameters, secrets in params leak into agent logs and traces. Must use server-side secret injection via environment variables (PLATFORM_VIMEO_KEY is checked but _apiKey override bypasses it).
Tool names lack action verbs. Rubric requires names starting with verbs (get_, search_, list_). Current names ('video', 'user', 'channel', 'categories') are nouns. LLMs rely on verb-first naming to infer intent. Should be: get_video, search_videos, get_user, list_categories, etc.