Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses payment requirements (API key or per-call cost) and the default behavior of returning all chains when omitted, which is useful. However, it does not mention rate limits, error handling, or whether the operation is read-only (though it implies a read). The absence of any note on response structure is partially mitigated by the existence of an output schema, but other behavioral traits remain undisclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.