An Express-based server that provides MCP (Model Context Protocol) endpoints to fetch tweets from Twitter/X using the Twitter API v2
Single tool 'get_tweets' has a basic description (67 chars) and minimal input schema. The description lacks WHEN to use it, prerequisites, or return structure. Input schema defines only 'username' as string with minimal description (29 chars). No output schema documented. No error handling guidance. No parameter constraints (e.g., username format, result limits). Tool does not follow LLM-optimized description patterns (target 50-200 chars). No pagination support despite Twitter API returning lists. Naming is acceptable (verb_noun), but overall definition quality is far below production baseline.
Fetches recent tweets from a specified Twitter/X username using the Twitter API v2
No output schema documented. LLM cannot infer what fields to expect from the response, preventing downstream tool chaining and forcing manual parsing.
Parameter description too short (29 chars). 'The Twitter/X username to fetch tweets from' lacks format constraints, examples of valid input, or guidance on username vs handle format.
Tool description lacks WHEN to use it and prerequisites. Should state: 'Fetches up to 10 recent tweets from a public Twitter/X account. Requires a valid Twitter API v2 bearer token. Returns tweet IDs, text, creation dates, and author info.'
No pagination support. Twitter API returns lists but tool has no limit or offset parameters. Large result sets will blow context window. Should accept 'max_results' (1-100) and 'next_token' parameters.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 36 | 2026-07-28+ | v2 |
No error handling guidance. Catch block returns generic 'Failed to get tweets' with no actionable recovery steps. Should distinguish: invalid username (user-fixable), API rate limit (retryable), auth failure (fatal).