Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It usefully states that the tool returns inputs (with units, ranges, defaults), outputs, assumptions, and tables, giving a clear expectation of content. It does not mention any side effects or limitations, but for a describe-only tool this is largely sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.