Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. While 'stop (pause)' implies a state change, it doesn't clarify whether this is reversible, if it affects data transfer, what permissions are required, or what the output contains. The description adds minimal behavioral context beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.