MCP server for media-related tools including search functionality
Single tool 'search' with minimal definition. Input schema present but lacks descriptions for parameters. No output schema documented. No error handling guidance. No parameter constraints (enums, ranges). Does not follow verb_noun pattern clearly ('search' alone is generic). Fails multiple critical checks from rubric section B (descriptions) and D (schemas & output).
Tool 'search' has NO description. LLMs cannot determine when or why to select this tool.
Input parameters 'query' and 'max_results' lack descriptions. LLMs cannot infer what 'query' searches (media? podcasts? all content?) or what 'max_results' range is valid (1-10? 1-1000?).
No output schema documented. LLMs cannot plan downstream calls or extract relevant data. Rubric baseline: 100% of A+ tools have documented return types.
No error handling guidance. If search fails (network error, invalid query, no results), LLM has no recovery path. Rubric section E requires actionable error messages.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 39 | 2026-07-28+ | v2 |
Parameter 'max_results' is unbounded integer with no min/max constraints. LLM could pass 999999, causing timeout or resource exhaustion. Rubric section C requires numeric bounds.