Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds no behavioral context beyond a restatement of the function, such as behavior when no presentation is open, error handling, or any side effects. Since the description carries no extra value beyond the annotations, it scores low on this dimension.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.