Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses beyond annotations: it explains the automatic clearing of worn flairs via FK ON DELETE SET NULL, the required 'can_manage_flair' authority, and that it writes an audit envelope. These behavioral traits are not present in the annotations (destructiveHint, readOnlyHint) and add essential context about side effects and prerequisites.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.