FDE live-coding round: "Build a minimal tool-calling agent in 45 minutes." What do you build, and what do interviewers look for?

import json

TOOLS = {
    "get_order_status": {
        "description": "Get status of an order by order_id (e.g. 'ORD-123').",
        "parameters": {"type": "object",
                       "properties": {"order_id": {"type": "string"}},
                       "required": ["order_id"]},
        "fn": lambda order_id: {"order_id": order_id, "status": "shipped"},
    },
}

def run_tool(name, args):
    if name not in TOOLS:
        return {"error": f"Unknown tool '{name}'"}
    try:
        return TOOLS[name]["fn"](**args)
    except TypeError as e:            # bad / missing arguments
        return {"error": f"Invalid arguments: {e}"}

def agent(user_msg, llm, max_steps=8):
    messages = [{"role": "system", "content": "You are a support agent. Use tools; never invent order data."},
                {"role": "user", "content": user_msg}]
    schemas = [{"name": n, "description": t["description"], "parameters": t["parameters"]}
               for n, t in TOOLS.items()]
    for step in range(max_steps):
        reply = llm.chat(messages=messages, tools=schemas)   # wrapper over your provider SDK
        messages.append(reply.as_message())
        if not reply.tool_calls:
            return reply.text                                  # final answer
        for call in reply.tool_calls:
            result = run_tool(call.name, call.arguments)
            print(json.dumps({"step": step, "tool": call.name, "args": call.arguments, "result": result}))
            messages.append({"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)})
    return "I couldn't complete this within the step limit. Here is what I found so far..."