Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations available, the description carries the full burden of behavioral disclosure. 'Lock an object' provides no information about the effects of locking, permission requirements, reversibility, or how it interacts with other operations such as 'unLock', leaving the agent without critical context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.