Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds genuinely useful behavior: the nonce count is interpreted differently for wallets vs contracts and both are reported under their own names. It also discloses input requirements and pricing/auth model, going well beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.