Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds context about 'privacy-minimized' data and the types of states covered, which is useful but does not disclose additional behavioral traits such as error conditions or response size limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.