Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered structurally. The description adds useful behavior context in the free quota (200 calls per day per IP) and a pricing URL for keyed volume, though it does not say what the response actually contains.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.