Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, which already convey safety and idempotency. The description adds no behavioral context beyond what annotations provide, such as what 'buildServers' means operationally, whether it triggers processes, or what the response contains. However, it doesn't contradict annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.