Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered without the description. 'Currently active' adds the notion of live state rather than a persisted setting, which is mildly useful, but nothing about what 'active' means operationally (e.g. whether it requires a session, daemon, or can fail).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.