Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, and destructiveHint, establishing a safe, non-mutating operation. The description adds valuable behavioral context beyond annotations: dates are inclusive of both ends, only England and Wales bank holidays are considered, and the bank holiday dataset is limited to 2026–2027, outside which only weekends are excluded. This information meaningfully affects results and is not available from annotations alone.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.