Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already communicate read-only, non-destructive, and idempotent behavior. The description adds the authentication requirement and what the call returns, plus the workflow cue that this is a preflight quote before a mutating transfer operation. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.