Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and 'Xem' does communicate a non-mutating read. It also discloses the returned fields (position, size, material, structural diagram), which is real value since there is no output schema. However, it omits error behavior when the object is not found and any access/permission expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.