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, but it says nothing about what the returned marker data includes, whether selection affects results, or if this is a read-only operation. The description adds no behavioral traits beyond the fact that it gets clip markers.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.