Loading ToolBench
MCP server with Twitter integration and basic math tools
Both tools have minimal descriptions (10-15 chars, well below the 50-200 char baseline for LLM-optimized descriptions). Parameter descriptions are entirely missing (null values in schema). No output schemas documented. Tool names lack clarity on side effects. addTwoNumbers is acceptable naming, but createPost should clarify it posts to Twitter. No error handling guidance, no validation rules, no recovery paths. This server falls into the F-D range due to pervasive omissions across all quality dimensions.
Add two numbers
Create a tweet
All parameter descriptions are null. LLMs cannot infer what 'a', 'b', or 'status' mean without explicit descriptions. Pattern requires every parameter to have a non-empty description.
Tool descriptions are too short (10-15 chars vs. baseline 50-200 chars). 'Add two numbers' and 'Create a tweet' lack context on when to use, what happens, and prerequisites. LLMs need richer descriptions for proper tool selection.
No output schemas documented. Callers cannot predict what fields to expect. addTwoNumbers returns a text summary; createPost returns a tweet confirmation. Both should declare structured return types.
createPost exposes Twitter API credentials via environment variables but lacks any error handling or permission checks. No audit trail, no rate limiting, no dry-run option for a destructive operation.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 37 | 2026-07-28+ | v2 |
createPost tool name does not clarify it posts to Twitter. Ambiguous names like 'createPost' could mean blog post, forum post, or social media. Should be 'create_twitter_post' or 'post_tweet' for clarity.