Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even with readOnlyHint=true lowering the baseline, the description discloses significant behavioral detail: it returns observed state when rate-limited, never presents unobserved attempts as verdicts, and normalizes domains. This goes well beyond the annotation and schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.