Twitter Api45 MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries the full disclosure burden. It reveals important implementation details—that it scans the user's 'latest tweets' rather than using a direct lookup— which explains the temporal limitation. However, it omits critical behavioral context: return value format (boolean vs object), error handling for private users, and rate limit implications of timeline scanning.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief (two sentences) and front-loads the primary action, but wastes words with 'This endpoint' (redundant for MCP tools) and uses grammatically incorrect 'get' instead of 'gets'. The WARNING is appropriately placed at the end, but 'needed tweet' is imprecise terminology that reduces clarity per word.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema and annotations, the description provides minimal viable context by explaining the temporal scope limitation. However, it fails to describe the return structure (what constitutes a 'found' vs 'not found' retweet), possible error states, or the practical limit of 'latest' tweets (how many days/hours back), leaving operational gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

While the schema has 100% field coverage, the parameter descriptions are empty placeholders ('Example value: '). The description text mentions 'user' and 'needed tweet' which map to the parameters, but fails to compensate for the schema gaps by specifying formats (e.g., whether screenname includes '@', if tweet_id is numeric) or constraints, leaving parameter semantics under-specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a user's recent tweets to check for a specific retweet ('checks if there is a retweet of the needed tweet'). However, it uses awkward phrasing ('needed tweet' instead of 'specified tweet') and fails to explicitly distinguish its purpose from the sibling 'retweets' tool, which likely lists all retweets rather than checking a specific user's timeline.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a negative usage constraint via the WARNING about old retweets, implying the tool shouldn't be used for historical checks. However, it lacks explicit guidance on when to prefer this over the 'retweets' sibling tool or other alternatives, and doesn't mention prerequisites like the target user's visibility settings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.