Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it as readOnly, non-destructive, and not open-world. The description adds that it is informational and cautions to confirm with local counsel, which provides practical context about the reliability of the output. It aligns with annotations without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.