Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only mark readOnly, openWorld, idempotent, and destructive as false; the description adds a meaningful behavioral consequence by saying the call 'Creates an inbound sponsor lead the org will follow up on.' This discloses state-changing behavior and follow-up expectation beyond what the annotation booleans convey, though it omits details like duplicate handling or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.