Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and idempotentHint=false, so the agent knows this writes something and that repeated calls are not equivalent, but the description adds no context about where the STL/viewer file is written, whether it overwrites, how long it takes, or what happens if no model is open. For a file-producing tool the output destination is essential behavioral information and is entirely absent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.