Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context beyond those annotations: it is free with no credit charge, cannot set moderation states, and has a specific precondition for re-activation. There is 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.