Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide readOnlyHint=true, which already declares safety. The description adds that it uses 'x402 pay-per-call USDC on Solana' but does not explain the actual behavior: Does it return a payment link? Does it redirect to a wallet? Does it require user interaction? Does it charge immediately? Without this, an agent cannot predict what happens after calling this tool. The description does not contradict the read-only hint, but it fails to disclose the operational flow, which is a significant gap for a no-parameter tool with no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.