Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds conditional return details: 'forum chats may include topics up to topics_limit; user targets may include common_chats up to common_chats_limit,' which is useful behavioral context not provided by annotations. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.