Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark destructiveHint=true, but the description adds substantial behavior: it removes membership, blocks rejoin/posting/commenting/voting, temporary bans auto-lift with notification, and the user can appeal via colony_appeal_ban. Also discloses edge cases (founders and last moderator can't be banned). This goes well beyond the annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.