Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the operation as readOnly and idempotent, so the safety profile is covered. The description adds the behavioral clue that rejection reason is only returned when applicable, but it does not disclose other useful context such as possible status values, invalid ad_id behavior, or response shape.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.