Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description adds no behavioral context (e.g., error handling, permissions, or what happens if the segment group does not exist). With annotations providing the safety profile, the description misses opportunities to add value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.