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. While 'Trigger' implies an action that initiates something, the description doesn't specify what happens after triggering (e.g., whether tests run immediately, if results are returned, if this is a one-time or recurring trigger, or what permissions are required). This leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.