Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations the description carries the full burden, and it does disclose one genuinely useful behavioral detail: the counting boundary is exclusive of from_date and inclusive of to_date, which pre-empts off-by-one errors. It omits everything else an agent needs — rule resolution, how region/jurisdiction alter the result, the NZ default, and error behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.