Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover key behavioral traits (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the description doesn't need to repeat these. It adds minimal context by specifying 'previously deactivated,' but doesn't elaborate on effects like permission restoration or error conditions. No contradiction with annotations exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.