Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral context on top: the result is a live capture that may be degraded, it carries capture time/hash and match labels, cursors are bound to gene/snapshot/sort, and abstracts are absent. 'Contains no abstracts' is a return-value detail that partially duplicates the output schema, keeping it from a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.