Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds one genuinely useful trait beyond that: exported CSV files retain their own copy until deleted separately, which tells the agent deletion is not global. It says nothing about permissions or reversibility ('for good' only implies permanence).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.