Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description discloses important behavior: it returns only a URL, it does not charge the AI, the human must enter their own card, the site remains on the free plan until checkout completes, and authentication requires a claim secret as a bearer token. This is substantial behavioral context that annotations alone do not provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.