Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It doesn't mention whether the list returns full paths, whether it recurses into subdirectories, whether it includes disabled or commented scripts, or whether output is limited to project root. Basic read operation is implied but details are missing. As a read-only listing operation, the risk surface is low, which mitigates the lack of detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.