Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint and idempotentHint annotations, safety is already disclosed. The description adds valuable behavioral context: volatility and rates are in percent (not decimals), and the output includes d1/d2. It also specifies European-only scope, a key limitation. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.