Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool 'checks' status and statistics, implying a read-only operation, but doesn't clarify authentication needs, rate limits, data freshness, or what 'recent' means. This leaves significant behavioral gaps for a monitoring tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.