Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only indicate mutability and destructiveness; the description adds real behavioral detail: accepting lifts the ban and records an 'unban' audit row, while rejecting closes the appeal and relays the note. It also notes equivalence to the web and JSON API flows, which helps set expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.