Good point that schema validation checks structure but not whether the product exists or the user is allowed to see it; that gap is easy to miss. A check I'd add to the workflow test is reading the saved trace afterwards: does the assistant's final answer match what the tool really returned, for example saying a quotation was prepared when prepare_quotation errored? AiEnsured agentest runs that kind of trace check (pip install agentest-ai, 165 tests), and developers are welcome to enhance and contribute.