Loading ToolBench
Local-first Spotify playback, library, playlist, audio, and DJ tools.
Critical gaps across both tools. spotify_status has a minimal empty input schema {} with no parameter descriptions. spotify_render_results is inferred from a script filename (scripts/check_release.py) rather than explicitly registered in the server code, cannot verify actual tool definition, schema, or parameters. Both tools have extremely short descriptions (under 100 chars) that lack context on WHEN to use them, WHAT they return, or any prerequisites. No documented output schemas visible. No error handling guidance. The server exposes only 2 tools with minimal definition quality, making it unsuitable for production agent use.
Render structured Spotify results in the MCP Apps UI.
Check whether local Spotify configuration and authentication work.
spotify_render_results tool definition not visible in server code, only inferred from script filename. Cannot verify actual schema, parameters, or registration.
spotify_status has empty input schema {} with zero parameter descriptions. No documentation of what the tool returns, when to call it, or what 'configuration and authentication work' means operationally.
Both tool descriptions are under 100 characters and lack WHAT/WHEN/WHY context. 'Check whether local Spotify configuration and authentication work' does not explain what the LLM should do with the result, what fields are returned, or when to call it vs other tools.
No documented output schemas for either tool. LLMs cannot plan downstream calls or extract required fields (e.g., user_id, display_name) without knowing the response structure.
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 36 | 2025-06-18+ | v2 |
No error handling guidance. If spotify_status fails (e.g., auth token expired, Spotify API unreachable), the tool provides no recovery hint. LLM cannot determine if the error is retryable, user-fixable, or fatal.