Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility for behavioral disclosure. It states the core behavior (splitting into two) but omits important details such as whether the draft is mutated immediately, any validation on atSec (e.g., must lie within segment duration), and what identifiers the resulting segments will have.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.