Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It indicates a read-only operation through 'Retrieves', but does not disclose what the response contains, whether the job can be polled, or any error behavior. The disclosure is minimal but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.