Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The 'read-only' phrase is the sole behavioral disclosure, which is useful but minimal. With no annotations provided, the description carries the full burden, yet it omits details like whether it returns live data, cache, or any side effects. For a status tool this may be sufficient, but it adds little beyond the purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.