An MCP server for indoor sports and simulator venue operations. Sample data only; safe to run standalone.
Single tool with minimal schema and generic description. Input schema is empty object {} with no parameter definitions, violating core schema requirements. Description is present but generic (79 chars), lacking actionable context for LLM selection. No parameter descriptions, no output schema documentation, no error handling guidance. Tool does one thing (list bays) but lacks the rigor expected even for simple read-only operations.
Returns every bay, cage, or court the venue has, with its current status and hourly rate. Sample data only in this build.
No output schema documented. LLM cannot infer response structure (fields, types, nesting). Must document that response contains 'bays' array with Bay objects (id, name, kind, status, hourly_rate_usd).
Description lacks context for LLM selection. Does not explain WHEN to call this tool vs alternatives, what prerequisites exist, or how results should be used. Generic 'Returns every bay...' does not guide agent reasoning.
No pagination support. Tool returns hardcoded 3 items, but production venues may have dozens or hundreds of bays. Must add limit/offset parameters and document max result size.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 43 | 2026-07-28+ | v2 |
No error handling or recovery guidance. If venue data is unavailable or malformed, LLM receives no actionable error message or next steps.