A Flask-based MCP server that provides Twitter-like functionality with context management and OpenAI integration for analyzing tweet data
This server has critical definition quality gaps. All three tools have minimal descriptions (10-20 chars, well below the 50-200 char baseline for LLM-optimized tools). Input schemas are present but lack parameter descriptions, the rubric requires every parameter to have a description explaining what it controls. Output schemas are completely undocumented. Error handling is minimal (basic missing-param checks only). The server is not a true MCP implementation, it's a custom Flask HTTP wrapper that does not follow MCP protocol patterns. Tool definitions appear inferred from code rather than explicitly registered via MCP mechanisms.
Fetches a tweet by ID and stores it in context
Retrieves previously stored context data by key
Searches for tweets matching a query and stores results in context
Tool descriptions are critically short (10-20 chars). Rubric baseline is 50-200 chars for LLM-optimized tools. Current descriptions lack WHAT the tool does, WHEN to use it, and any prerequisites.
Input parameter 'tweet_id' and 'query' lack descriptions. Rubric requires every parameter to have a non-empty description explaining what it controls. LLMs cannot infer parameter meaning from names alone.
Output schemas are completely undocumented. Rubric requires documenting the output schema so LLMs know what fields to expect and can plan downstream tool calls. No return type documentation visible.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 28 | 2026-07-28+ | v2 |
Error handling is minimal. Only basic 'Missing parameter' checks. No recovery guidance, error categorization (retryable vs fatal), or actionable error messages. Rubric requires errors to tell the LLM what to do next.
Tool definitions are inferred from code (openai_agent.py methods) rather than explicitly registered via MCP protocol.