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. 'View' weakly implies a read-only operation, but the description does not mention whether it is safe, what side effects might occur, how results are scoped, or what the output looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.