Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden for behavioral disclosure. It only states the tool 'generates a ready-to-use backend endpoint' without clarifying whether it returns code, writes files, or requires existing setup. No mention of side effects, output format, or limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.