Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructive and non-read-only behavior, but the description adds significant context: the action cannot be undone, associated results are deleted, and existing schedules are preserved. These are non-obvious behaviors that the agent cannot infer from the schema or annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.