Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, which cover safety and behavior. The description adds minimal behavioral context beyond 'source-aware,' which is more of a feature than a behavioral trait. It does not contradict the annotations, and it does not add significant operational details such as pagination or return behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.