Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds no new behavioral details (e.g., pagination behavior, default ordering, or return shape), but it is consistent with annotations. With annotations present, the low bar is met.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.