Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds two pieces of context beyond that: the required `billing:read` scope and the fact that results are bounded to the current billing period, both of which materially affect a call.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.