Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate the operation is not read-only and is not destructive, but the description adds no details about side effects (e.g., whether deployment overrides the current live version, requires a commit, or is reversible). The agent is left unaware of what actually happens during deploy, making this a significant transparency gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.