Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of explaining behavior. 'Select a component in the editor' reveals the action but not side effects such as clearing previous selection, focusing/zooming the view, whether an open document is required, or what happens if the designator is not found. These are significant unknowns for a UI-state-mutating operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.