Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, which adequately cover the safety profile. The description adds the unit list but no additional behavioral context such as rounding, precision, or error handling, so it provides only baseline value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.