Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint and openWorldHint already declared, the description still adds genuinely useful operational context: a pay-per-call model ($0.002 USDC via x402, multiple chains) and, crucially, that failed calls are not charged. It also discloses that registry codes are passed through raw rather than normalized, which affects how results must be interpreted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.