Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false). The description does add genuinely non-obvious context: the response includes the merchant's encryption key for end-to-end encrypted order details. It does not mention any auth/permission requirements for retrieving that key, which is the most security-relevant behavior here.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.