Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the agent knows this is a non-idempotent write that touches external systems. The description adds nothing beyond that: no note on duplicates, failure modes, required permissions, or what the response contains (e.g., new lead ID).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.