Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, covering safety and idempotency. The description adds 'high-frequency', hinting at usage pattern but no specific behaviors (e.g., rate limits, side effects). With annotations doing heavy lifting, the description provides minimal extra transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.