MCP server for accessing YouTube data including trending videos, subscribed channels, and user activity
All three tools have basic descriptions and parameter schemas, but fall short of production quality. Descriptions are minimal (10-50 chars), lack context on WHEN to use each tool, and omit prerequisites. Parameters have types and defaults but lack descriptions entirely, LLMs cannot infer what 'region_code' or 'max_channels' control without explicit guidance. No output schemas documented. Error handling returns raw API errors without recovery guidance. Tools lack idempotency hints and do not indicate they are read-only in descriptions. No pagination support despite potentially large result sets.
Fetch the most recent uploads from subscribed YouTube channels.
Fetch trending YouTube videos.
Fetch the most recent activity from the authenticated user.
Parameter descriptions missing entirely. 'region_code', 'max_channels', 'max_results' have no descriptions, LLMs cannot infer what values are valid or what each parameter controls.
Tool descriptions are too brief (10-50 chars) and lack context. 'Fetch trending YouTube videos' does not explain WHEN to use this vs alternatives, what prerequisites exist (OAuth setup), or what the output structure is.
No output schema documented. Tools return formatted strings, but LLMs cannot parse structure or extract IDs for chaining. Baseline: 100% of A+ tools document return types.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2026-07-28+ | v2 |
Error handling returns raw API error text without recovery guidance. 'Error: {error_text}' tells LLM nothing about whether to retry, ask user, or abandon. Baseline: errors must guide next steps.
No pagination support. Tools accept max_results but do not return cursors, offsets, or total counts. Large result sets will blow context window; no way to fetch next page.