Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide read-only, open-world, idempotent, and non-destructive hints. The description adds value beyond annotations by clarifying default chain and accepted chain identifiers, but does not delve into other behavioral traits like caching or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.