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 merely restates the tool's purpose and adds no information about read-only intent, pagination, rate limits, or authentication. The term 'list' weakly implies a safe read operation, but the description adds no transparency beyond the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.