Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that the tool uses a configured route and focuses on proxy vs full-tunnel VPN limitations, which is consistent with the annotations but does not go deeper into result format, external requests, or potential variability.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.