Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds context beyond the annotations by using the word 'guarded' and specifying the precondition 'armed sweep or burst.' However, it does not explain the effects of triggering, potential errors, or the purpose of the confirm_trigger parameter. Given that annotations already indicate a non-read-only, non-destructive action, the description provides moderate additional behavioral context but not deep transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.