Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide only a title ('Duplicate Border') and no read-only or destructive hints, so the description carries the full burden. 'Extract border curves' suggests creation of new curve geometry, but it does not disclose whether the original object is modified, what output is produced, how layers are handled, or what happens with invalid inputs. This is a minimal behavioral statement rather than a transparent one.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.