Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/closed-world, and an output schema exists, so the description correctly focuses on behavioral scope: income independence and explicit exclusions (dubbele kinderbijslag, woonlandfactor, 16-17 without school). This adds real value, though it doesn't discuss edge behavior like invalid age inputs or how the excluded cases are handled.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.