Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already disclose read-only, idempotent, non-destructive behavior. The description adds that the tool returns dated events with ingredient, trade name, applicant, application, patent/use-code, and exclusivity-code context, which is useful beyond the schema. It omits minor details like limit clamping or event_type filtering, but the annotation coverage lowers the burden.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.