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 states the action but does not explain what setting an executor to 'top priority' entails, whether it is reversible, how it affects other executors, or what the return message contains. Critical side effects and operational context are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.