Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and open-world behavior. The description adds useful input-domain context (product-bag vs. packing-list, 1D vs. 2D) but does not disclose return format, error behavior, or how the 'includes' option affects output. It provides some value beyond annotations but not a rich behavioral picture.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.