Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It does state a key side effect ('invalidates the old value'), which is helpful. However, it does not mention the need for an explicit confirmation, the fact that a new secret will be generated (and how that new secret is surfaced to the agent/user), or any other possible operational consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.