MCP server for managing votes with mock API integration and local note storage
Critical gaps across all dimensions. 4 of 6 tools lack descriptions entirely (get_votes, search_votes, add_votes, write_note). All 6 tools have parameter descriptions set to null, violating the baseline that 100% of A+ tools have parameter descriptions. Tool names are reasonable (verb_noun pattern) but lack supporting documentation. No output schemas documented. No error handling guidance. No pagination for list-returning tools. This server would not pass code review.
Add two numbers
Read and return the content of the saved note
4 of 6 tools have no description (get_votes, search_votes, add_votes, write_note).
All 6 tools have null parameter descriptions. Rubric baseline: 100% of A+ tools have parameter descriptions. LLMs cannot infer parameter meaning from names alone (e.g., 'query' could be SQL, natural language, or regex).
No output schemas documented. Rubric baseline: 100% of A+ tools have documented return types. LLMs cannot plan downstream calls or extract data without knowing response structure.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
get_votes returns unbounded list with no pagination. Rubric: tools returning lists must accept limit/offset and return total count. Large results blow context window.
No error handling guidance. Tools call external API (httpx.get/post) without try-catch or recovery hints. If API fails, LLM receives raw exception with no actionable next step.