RAG on local files with MCP - provides semantic search and context retrieval from indexed local documents (PDF, CSV, DOCX, MD, TXT)
Single tool with reasonable naming but significant gaps in description quality, parameter documentation, and output schema definition. Tool name 'minima-query' is action-oriented (acceptable) but description is brief and lacks context on when/how to use it. Input schema is present and typed, but parameter description is minimal (10 chars: 'context to find'). No documented output schema, callers cannot predict response structure. Error handling exists but lacks recovery guidance. Prompts feature is listed but implementation is incomplete (get_prompt handler has syntax error 'Mcp' without definition). Overall resembles a D+ grade: basic functionality present but multiple production-readiness gaps.
Find a context in local files (PDF, CSV, DOCX, MD, TXT)
Tool description is under 20 characters and lacks LLM-selection context
Parameter 'text' has 10-character description; LLM cannot infer semantics, format, or constraints
Output schema not documented; callers cannot predict response structure or chain downstream tools
Error handling returns McpError but lacks actionable recovery guidance for LLM
Prompts feature incomplete: get_prompt handler has undefined name 'Mcp' (syntax error); prompt argument description is generic
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | D | 53 | <=2025-11-25 | v2 |
| 2026-03-09 | F | 31 | - | v1 |
No input validation rules documented (e.g. max length, expected format for 'context' parameter)