Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds useful behavioral context by explaining what each direction accepts and giving concrete examples like '1430', '14:30', and '2:30' with a meridiem. It does not discuss edge cases such as invalid input or 2400 handling, but that is a minor gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.