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 notes the restart requirement, but it does not mention whether the operation updates or creates the key, what happens if the key is invalid, whether it is destructive, or any error conditions. The restart note is helpful but insufficient for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.