Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, and 'inspect dom object' provides only a weak implication of read-only behavior. It does not state whether the operation mutates state, requires a running Premiere Pro session, returns a result, or could fail, so the agent has insufficient information about the tool's actual behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.