Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as read-only, non-destructive, idempotent, and closed-world, which covers key behavioral traits. The description doesn't add behavioral context beyond these annotations, but it also doesn't contradict them. Since annotations provide good coverage, the bar is lower, and the description doesn't need to repeat this information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.