Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety characteristics (readOnlyHint, idempotentHint, non-destructive), so the description does not need to repeat them. The description adds workflow and return-field context, but does not disclose any distinctive behavioral traits beyond what annotations and the schema provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.