Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and 'without overwriting' is consistent with that safety profile. The description adds the useful constraint that existing files are not clobbered, but says nothing about failure behavior when the target exists, whether the working document's path changes after the copy, or where relative paths resolve.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.