MCP server with Twitter integration and basic arithmetic tools
Both tools have minimal descriptions (under 50 chars) and parameter descriptions are entirely missing (null). addTwoNumbers lacks context for when to use it; createPost has a typo ('formally known as'). Neither tool documents output schema, error handling, or recovery guidance. Parameters lack type hints in descriptions (e.g., 'status' could be HTTP status, project status, or boolean). No input validation, no pagination support, no idempotency guarantees. Security issue: Twitter credentials are injected server-side (good), but no audit logging or permission gates. Schemas are present but descriptions are critically deficient.
Add two numbers
Create a post on X formally known as Twitter
All parameter descriptions are null. LLMs cannot infer what 'a', 'b', or 'status' mean without explicit descriptions. Pattern requires non-empty descriptions for every parameter.
Tool descriptions are too short (<50 chars) and lack context. 'Add two numbers' does not explain when to use this tool vs. alternatives, what it returns, or prerequisites. 'Create a post on X formally known as Twitter' contains a typo and no guidance on rate limits, authentication, or failure modes.
No output schema documented. LLMs cannot plan downstream tool calls or extract required fields. Both tools return {content: [{type: 'text', text: string}]} but this is not declared in tool metadata.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 37 | 2026-07-28+ | v2 |
createPost is a destructive operation (WRITE risk) with no confirmation step, dry-run option, or error recovery guidance. If the tweet fails, the LLM has no guidance on retry strategy or compensation.
No audit logging or permission gates. createPost calls Twitter API with server-side credentials but does not log who invoked it, when, or with what parameters. No permission check to verify the agent is authorized to post.