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 that it does not render, which implies non-destructiveness, but it does not explicitly confirm that no files are changed or that it is safe to run multiple times. Additional details about side effects or return format would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.