Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a read operation ('Get details') but does not specify any safety traits (e.g., read-only, non-destructive) or other behaviors like data freshness, error handling, or rate limits. The addition of 'including categories and levels' adds some output context but does not go beyond the obvious.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.