Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It implies a state change but does not explain whether the tool toggles arming, what `armed: null` means, whether repeated calls have side effects, or whether recording must be stopped. This is a significant transparency gap for a state-mutating tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.