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 does not reveal that the operation is destructive, what side effects occur (e.g., deleting volumes), or whether a running container can be removed without force. The description only restates the tool's name without any additional behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.