Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds the 'active' filter, which is a behavioral constraint beyond annotations. However, it does not disclose what happens if no active request exists or describe the response format, leaving some transparency gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.