Loading ToolBench
MCP server for managing and monitoring RabbitMQ queues, topics, and subscriptions
Single tool 'Purge' has critical definition gaps. Tool name lacks action clarity (should be 'purge_queue'). Description is minimal (14 chars, below 20-char threshold). Input schema present but parameter 'queue' lacks description entirely. No output schema documented. No error handling guidance. Tool is marked destructive but lacks confirmation/dry-run pattern. Violates 8+ core patterns from the rubric.
Purges a queue
Tool description 'Purges a queue' is 14 characters, below 20-char minimum. LLM cannot determine when/why to select this tool.
Parameter 'queue' has no description. LLM cannot infer whether to pass queue name, ID, or pattern.
No output schema documented. Return type is string 'purged {queue}' but LLM has no structured expectation. Violates pattern: document output schema.
Destructive tool lacks confirmation/dry-run pattern. Purge is irreversible, should support dry-run or require explicit confirmation before executing.
No error handling guidance. Tool returns success string but does not document failure modes (queue not found, permission denied, timeout). LLM has no recovery path.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 21 | <=2025-11-25 | v2 |