Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, non-destructive, idempotent, and open-world hints. The description adds minimal behavioral context (e.g., returning ratings and release dates) but does not disclose pagination behavior or data freshness. With strong annotations, the description provides marginal extra value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.