Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the full safety profile (readOnly, idempotent, non-destructive, closed-world), and an output schema exists, so return values need not be described. The description adds only that results are 'exact' and lists the feast categories covered, which is modest added context beyond structured fields.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.