The problem with CLIs is that unless it's a super well documented CLI like `gh`, the LLM will have a hard time figuring out how to use it from `--help` alone unless it's a really simple tool. If you want to do something complex, like create a JIRA issue, you either need to put the full issue schema in `--help` so that the LLM knows how to pass an issue or else you can use MCP which bakes tool schemas into the protocol.
That's easily solved by wrapping it in a skill. And every time it fails, once you are done you ask it to update the skill with what it learned. A couple iterations later and it will be solid.