Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/idempotent annotations, the description discloses important behavior: only visibility='public' claims are returned, private state never leaks, accuracy is computed as confirmed/(confirmed+refuted) over resolved claims, becomes null when n < 5, and sample-tier users are rejected. These are substantive, non-obvious behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.