Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructive behavior; the description adds the key nuance that all future instances are deleted, which is important for an agent to know before invoking. It does not describe past instances or permissions, but the additional scope context is valuable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.