Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, so the description doesn't need to repeat that. It adds valuable constraints: 'exactly one regular file' and 'same computer', which inform the agent about scope and potential failure modes. This goes beyond the schema and annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.