Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, and the description adds value beyond that: it discloses that results include what happened, when, and the current entity where one exists, and it explains the licence/policy continuation semantics. This is useful behavioral context without contradicting any annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.