Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior. 'Typed inference' hints at some inference behavior, but the description does not explain what is inferred, whether this is read-only, what side effects exist, or what the output represents. This is too thin for an agent to predict the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.