Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the safety profile is fully covered. The description adds useful behavioral context by revealing that results are limited to two specific operators (all their ports), which is knowledge the agent cannot get from annotations. It does not disclose result size, ordering, or what a port record contains.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.