Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the description's safety burden is light. However, it adds nothing beyond them: no supported unit identifiers, no precision/rounding behavior, no error behavior for invalid units. With annotations covering safety, the description still leaves the operational profile blank.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.