Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal readOnly=false, destructive=false, and idempotent=true, and the description adds valuable behavior: charging the wallet, optional tip donation, the rejection of already-finalized orders (supporting idempotency), and the no-card-payment limitation. The FINANCIAL warning further clarifies the risk profile.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.