Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the delete is a soft-delete, which is not implied by the annotations' destructiveHint=true (which could suggest a hard delete). It also mentions the token scope requirement, adding auth context beyond structured annotations. This goes beyond what annotations alone convey, though it doesn't describe reversibility or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.