Single tool 'whoami' has a minimal description (54 chars) and empty input schema. The description lacks context on when/why to call it, what it returns, or how it fits into workflows. No parameter descriptions exist (none required, but output schema is undocumented). Tool naming is acceptable but definition quality is severely limited by missing schema documentation and sparse description.
Return the verified token's claims as the server sees them.
No input schema visible in source code. Tool definition appears inferred from framework registration rather than explicitly declared with JSON Schema.
Tool description is 54 characters, below the 100-char minimum for actionable LLM guidance. Does not explain what 'verified token claims' means, when to call it, or what structure is returned.
Output schema is not documented. LLMs cannot plan downstream calls or extract fields without knowing the response structure (e.g., does it return user_id, email, roles, scopes?).
No error handling guidance. Tool description does not explain failure modes (e.g., invalid token, expired session) or recovery steps.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 39 | 2026-07-28+ | v2 |
Tool is read-only but lacks explicit idempotentHint annotation in schema. Agents cannot infer safety from the definition alone.