Ok, so agent swarm = tool calling where the tool is a LLM call and the argument is the prompt

Yes largely, although they’ve trained a model specifically for this task rather than using the base model and a bit of prompting.

Sort of. It’s not necessarily a single call. In the general case it would be spinning up a long-running agent with various kinds of configuration — prompts, but also coding environment and which tools are available to it — like subagents in Claude Code.