Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the description adds the formula context. It does not disclose additional behavior such as rounding, output type, or handling of percent inputs, but the formula is a useful behavioral clarification.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.