Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint and idempotentHint, so the description adds valuable behavioral context: it explains the meaning of spendable credits, that weeklyCredits is display-only, and how ad/referral grants work. This goes beyond the safety profile and provides critical semantics about the data returned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.