Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It discloses the core operation, the selection precondition, the through-point alternative, and the return dict keys. However, it does not state whether the original curve is kept or deleted, what happens when no curve is selected, or error/status behavior beyond the bare keys.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.