Loading ToolBench
An MCP server that provides motivational quotes based on mood
Single tool 'get_mood_quote' has a verb-based name (good), but the description is minimal (52 chars, below the 10-1024 baseline). Input schema is present with a 'mood' parameter, but lacks an enum constraint for the five valid moods (sad, happy, tired, excited, angry), forcing the LLM to guess valid values. Output schema is not documented, the response structure is inferred from code, not declared. No error handling guidance (e.g., what happens if an invalid mood is passed). No parameter description for the 'mood' input. Tool is read-only and simple, but lacks the rigor expected of production tools.
Retrieves a motivational quote based on the provided mood
Input parameter 'mood' lacks enum constraint and description. LLM cannot determine valid values without guessing.
Tool description is 52 characters, below the 10-1024 baseline and lacks WHAT/WHEN/WHY context. Does not explain when to use this tool or what it returns.
Output schema is not documented. Response structure (quote field) is inferred from code, not declared in tool definition. LLM cannot plan downstream calls.
No error handling guidance. Invalid mood returns a generic fallback message instead of actionable error (e.g., 'Invalid mood: must be sad|happy|tired|excited|angry').
No parameter description for 'mood' input. LLM cannot infer what values are valid or what the parameter controls.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 36 | 2026-07-28+ | v2 |