Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. 'Show' and 'check' clearly imply a read-only operation with no destructive side effects, which adds transparency. However, it does not disclose whether the credential check calls external courier APIs or what happens when credentials are missing/expired, leaving some behavioral ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.