Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states 'read-only', which conveys that the operation does not modify state, but it does not disclose what output is returned, whether authentication is required, or any side effects (though read-only implies none). This is minimal and insufficient for a tool in a complex system.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.