Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/idempotentHint/destructiveHint annotations, the description reveals concrete behavioral details: data comes from specific state DOT/RWIS sources, it covers only listed regions, it reports 'no road weather' outside that coverage, and the data is measured rather than modeled. This is exactly the kind of context that helps an agent reason about results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.