Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true, so the safety profile is covered. The description adds genuine behavioral context beyond that: the variant is removed from both the picker's list and the store, and it explains the referential-integrity consequence of a partial removal. It stops short of stating irreversibility or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.