Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavioral meaning: a payment method on file does not constitute spending approval, and human approval must be obtained using the current estimate. It does not discuss auth scoping (the platform-admin-only constraint lives in the schema) or rate/refresh characteristics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.