Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds useful behavioral context by specifying exact metrics and time windows (last hour, last day, per minute) plus the unique 'nest behind chain' measure, though it does not disclose return shape, gas price units, or data freshness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.