Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is pre-covered. The description adds useful behavior beyond that: the data is 'verified public', and the tool 'never collects personal data or creates an order', giving extra clarity on privacy and side-effect expectations. No contradiction with the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.