Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds useful context by explicitly mentioning 'token freshness,' which informs the agent that the tool also checks token validity, not just link status. This goes beyond the basic annotation details and clarifies the behavioral scope.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.