Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark destructiveHint and readOnlyHint, but the description adds valuable behavioral context: the deletion is a move to trash, scoped to the active account, and reversible from the web app. This goes beyond the annotations and clarifies the nature of the destructive action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.