Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. 'Flash the headlights' implies a vehicle control action but doesn't specify whether this requires the vehicle to be awake/online, what permissions are needed, whether it's rate-limited, or what the response looks like. It provides minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.