Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint=true and idempotentHint=true, the annotations already cover safety, but the description adds no behavioral context beyond that. It does not explain that login likely issues a session token, that it may require username/password (which are absent from the schema), or that it could have side effects like rate limiting. The description is too sparse to help an agent understand the operational implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.