Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the burden. It adds meaningful behavioral context by stating that the output covers the full history, is broken down by property type, and uses decimal fractions. It does not disclose data availability, missing-suburb behavior, or included property types, but for a simple read tool the core data shape is communicated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.