Loading ToolBench
Single tool with adequate schema but significant gaps in descriptions and parameter documentation. Tool name lacks action verb clarity. Input schema is present with proper types, but parameter descriptions are minimal (1-2 sentences). No output schema documented. Error handling returns YAML but lacks recovery guidance. Tool description is generic and does not explain when to use it vs alternatives or what the agent should expect.
Make a request to any PeakMojo API endpoint. Use the API documentation at /api/docs/categories to discover available endpoints.
Tool name lacks action verb. 'peakmojo_make_api_request' is generic; should be 'call_peakmojo_api' or 'query_peakmojo_endpoint' to signal intent clearly.
No output schema documented. Tool returns YAML text but LLM cannot predict structure, field names, or types. Agents cannot plan downstream calls or extract specific fields reliably.
Parameter descriptions are minimal (1-2 sentences). 'endpoint' lacks format guidance (does it require leading slash? what are valid paths?). 'params' and 'data' descriptions do not explain structure or constraints.
Error handling returns YAML dump of exception but no recovery guidance. 'Request error: <message>' tells agent nothing about retry eligibility, required fixes, or next steps.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 42 | <=2025-11-25 | v2 |
Tool description references '/api/docs/categories' as discovery endpoint but does not explain when/why to call it or what structure it returns. Agents lack guidance on endpoint discovery workflow.