Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already disclose the tool's safety profile, so the bar is lower. However, the description adds zero behavioral context beyond a generic 'Get Opportunity'. It does not describe return format, potential errors, or any special behavior, contributing nothing beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.