Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds minimal behavioral context beyond what annotations provide. Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, which fully covers safety and idempotency. The description's mention of 'rpc.discover' hints at a discovery operation but doesn't elaborate on what gets discovered. No contradiction with annotations exists, and the description doesn't add meaningful behavioral details like rate limits, authentication needs, or response format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.