教程：構建工具使用代理

教學：建構工具代理程式

本教程通過五個同心環構建一個日曆管理代理。每個環都是一個完整的、可運行的程序，它在前一個環的基礎上恰好添加一個概念。最後，你將手動編寫代理循環，然後用 Tool Runner SDK 抽象替換它。

示例工具是 create_calendar_event。其架構使用嵌套對象、數組和可選字段，因此你將看到 Claude 如何處理現實的輸入形狀，而不是單個平面字符串。

每個環都獨立運行。將任何環複製到新文件中，它將執行而無需來自早期環的代碼。

環 1：單個工具，單次轉換

最小的工具使用程序：一個工具、一條用戶消息、一次工具調用、一個結果。代碼有大量註釋，因此你可以將每一行映射到工具使用生命週期。

請求在用戶消息旁邊發送一個 tools 數組。當 Claude 決定調用工具時，響應返回 stop_reason: "tool_use" 和一個包含工具名稱、唯一 id 和結構化 input 的 tool_use 內容塊。你的代碼執行工具，然後在 tool_result 塊中發送結果，其 tool_use_id 與調用中的 id 匹配。

# Ring 1: Single tool, single turn.
# Source for <CodeSource> in build-a-tool-using-agent.mdx.

import json

import anthropic

# Create a client. It reads ANTHROPIC_API_KEY from the environment.
client = anthropic.Anthropic()

# Define one tool. The input_schema is a JSON Schema object describing
# the arguments Claude should pass when it calls this tool. This schema
# includes nested objects (recurrence), arrays (attendees), and optional
# fields, which is closer to real-world tools than a flat string argument.
tools = [
    {
        "name": "create_calendar_event",
        "description": "Create a calendar event with attendees and optional recurrence.",
        "input_schema": {
            "type": "object",
            "properties": {
                "title": {"type": "string"},
                "start": {"type": "string", "format": "date-time"},
                "end": {"type": "string", "format": "date-time"},
                "attendees": {
                    "type": "array",
                    "items": {"type": "string", "format": "email"},
                },
                "recurrence": {
                    "type": "object",
                    "properties": {
                        "frequency": {"enum": ["daily", "weekly", "monthly"]},
                        "count": {"type": "integer", "minimum": 1},
                    },
                },
            },
            "required": ["title", "start", "end"],
        },
    }
]

# Send the user's request along with the tool definition. Claude decides
# whether to call the tool based on the request and the tool description.
response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=tools,
    tool_choice={"type": "auto", "disable_parallel_tool_use": True},
    messages=[
        {
            "role": "user",
            "content": "Schedule a 30-minute sync with [email protected] and [email protected] next Monday at 10am.",
        }
    ],
)

# When Claude calls a tool, the response has stop_reason "tool_use"
# and the content array contains a tool_use block alongside any text.
print(f"stop_reason: {response.stop_reason}")

# Find the tool_use block. A response may contain text blocks before the
# tool_use block, so scan the content array rather than assuming position.
tool_use = next(block for block in response.content if block.type == "tool_use")
print(f"Tool: {tool_use.name}")
print(f"Input: {tool_use.input}")

# Execute the tool. In a real system this would call your calendar API.
# Here the result is hardcoded to keep the example self-contained.
result = {"event_id": "evt_123", "status": "created"}

# Send the result back. The tool_result block goes in a user message and
# its tool_use_id must match the id from the tool_use block above. The
# assistant's previous response is included so Claude has the full history.
followup = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=tools,
    tool_choice={"type": "auto", "disable_parallel_tool_use": True},
    messages=[
        {
            "role": "user",
            "content": "Schedule a 30-minute sync with [email protected] and [email protected] next Monday at 10am.",
        },
        {"role": "assistant", "content": response.content},
        {
            "role": "user",
            "content": [
                {
                    "type": "tool_result",
                    "tool_use_id": tool_use.id,
                    "content": json.dumps(result),
                }
            ],
        },
    ],
)

# With the tool result in hand, Claude produces a final natural-language
# answer and stop_reason becomes "end_turn".
print(f"stop_reason: {followup.stop_reason}")
final_text = next(block for block in followup.content if block.type == "text")
print(final_text.text)

預期結果

Output

stop_reason: tool_use
Tool: create_calendar_event
Input: {'title': 'Sync', 'start': '2026-03-30T10:00:00', 'end': '2026-03-30T10:30:00', 'attendees': ['[email protected]', '[email protected]']}
stop_reason: end_turn
I've scheduled your 30-minute sync with Alice and Bob for next Monday at 10am.

第一個 stop_reason 是 tool_use，因為 Claude 在等待日曆結果。發送結果後，第二個 stop_reason 是 end_turn，內容是給用戶的自然語言。

環 2：代理循環

環 1 假設 Claude 將恰好調用一次工具。實際任務通常需要多次調用：Claude 可能創建一個事件、讀取確認，然後創建另一個。解決方案是一個 while 循環，它持續運行工具並反饋結果，直到 stop_reason 不再是 "tool_use"。

另一個變化是對話歷史。與其在每次請求時從頭重建 messages 數組，不如保持一個運行列表並追加到它。每次轉換都會看到完整的先前上下文。

預期結果

Output

I've set up your weekly team standup for the next 4 Mondays at 9am with Alice, Bob, and Carol invited.

循環可能運行一次或多次，取決於 Claude 如何分解任務。你的代碼不再需要提前知道。

環 3：多個工具，並行調用

代理很少只有一個功能。添加第二個工具 list_calendar_events，以便 Claude 在創建新內容之前可以檢查現有日程。

當 Claude 有多個獨立的工具調用要進行時，它可能在單個響應中返回多個 tool_use 塊。你的循環需要處理所有這些塊，並在一條用戶消息中一起發送所有結果。遍歷 response.content 中的每個 tool_use 塊，而不僅僅是第一個。

預期結果

Output

I checked your calendar for next Monday and found an existing meeting from 2pm to 3pm. I've scheduled the planning session for 10am to 11am to avoid the conflict.

有關並發執行和排序保證的更多信息，請參閱並行工具使用。

環 4：錯誤處理

工具會失敗。日曆 API 可能拒絕有太多參與者的事件，或日期可能格式不正確。當工具引發錯誤時，使用 is_error: true 發送錯誤消息，而不是崩潰。Claude 讀取錯誤，可以使用更正的輸入重試、要求用戶澄清或解釋限制。

預期結果

Output

I tried to schedule the all-hands but the calendar only allows 10 attendees per event. I can split this into two sessions, or you can let me know which 10 people to prioritize.

is_error 標誌是與成功結果的唯一區別。Claude 看到標誌和錯誤文本，並相應地響應。有關完整的錯誤處理參考，請參閱處理工具調用。

環 5：Tool Runner SDK 抽象

環 2 到 4 手動編寫了相同的循環：調用 API、檢查 stop_reason、運行工具、追加結果、重複。Tool Runner 為你做這一切。將每個工具定義為函數，將列表傳遞給 tool_runner，並在循環完成後檢索最終消息。錯誤包裝、結果格式化和對話管理在內部處理。

Python SDK 使用 @beta_tool 裝飾器從類型提示和文檔字符串推斷架構。TypeScript SDK 使用帶有 Zod 架構的 betaZodTool。

Tool Runner 在 Python、TypeScript 和 Ruby SDK 中可用。Shell 和 CLI 選項卡顯示注釋而不是代碼；為基於 shell 的腳本保留環 4 循環。

預期結果

Output

I checked your calendar for next Monday and found an existing meeting from 2pm to 3pm. I've scheduled the planning session for 10am to 11am to avoid the conflict.

輸出與環 3 相同。區別在於代碼：大約一半的行數、沒有手動循環，架構與實現並存。

你構建了什麼

你從單個硬編碼的工具調用開始，以處理多個工具、並行調用和錯誤的生產形狀代理結束，然後將所有這些折疊到 Tool Runner 中。在此過程中，你看到了工具使用協議的每一部分：tool_use 塊、tool_result 塊、tool_use_id 匹配、stop_reason 檢查和 is_error 信號。

後續步驟

完善你的架構

架構規範和最佳實踐。

Tool Runner 深入探討

完整的 SDK 抽象參考。

故障排除

修復常見的工具使用錯誤。

# Ring 2: The agentic loop.
# Source for <CodeSource> in build-a-tool-using-agent.mdx.

import json

import anthropic

client = anthropic.Anthropic()

tools = [
    {
        "name": "create_calendar_event",
        "description": "Create a calendar event with attendees and optional recurrence.",
        "input_schema": {
            "type": "object",
            "properties": {
                "title": {"type": "string"},
                "start": {"type": "string", "format": "date-time"},
                "end": {"type": "string", "format": "date-time"},
                "attendees": {
                    "type": "array",
                    "items": {"type": "string", "format": "email"},
                },
                "recurrence": {
                    "type": "object",
                    "properties": {
                        "frequency": {"enum": ["daily", "weekly", "monthly"]},
                        "count": {"type": "integer", "minimum": 1},
                    },
                },
            },
            "required": ["title", "start", "end"],
        },
    }
]


def run_tool(name, tool_input):
    if name == "create_calendar_event":
        return {"event_id": "evt_123", "status": "created", "title": tool_input["title"]}
    return {"error": f"Unknown tool: {name}"}


# Keep the full conversation history in a list so each turn sees prior context.
messages = [
    {
        "role": "user",
        "content": "Schedule a weekly team standup every Monday at 9am for the next 4 weeks. Invite the whole team: [email protected], [email protected], [email protected].",
    }
]

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=tools,
    tool_choice={"type": "auto", "disable_parallel_tool_use": True},
    messages=messages,
)

# Loop until Claude stops asking for tools. Each iteration runs the requested
# tool, appends the result to history, and asks Claude to continue.
while response.stop_reason == "tool_use":
    tool_use = next(block for block in response.content if block.type == "tool_use")
    result = run_tool(tool_use.name, tool_use.input)

    messages.append({"role": "assistant", "content": response.content})
    messages.append(
        {
            "role": "user",
            "content": [
                {
                    "type": "tool_result",
                    "tool_use_id": tool_use.id,
                    "content": json.dumps(result),
                }
            ],
        }
    )

    response = client.messages.create(
        model="claude-opus-4-6",
        max_tokens=1024,
        tools=tools,
        tool_choice={"type": "auto", "disable_parallel_tool_use": True},
        messages=messages,
    )

final_text = next(block for block in response.content if block.type == "text")
print(final_text.text)

# Ring 3: Multiple tools, parallel calls.
# Source for <CodeSource> in build-a-tool-using-agent.mdx.

import json

import anthropic

client = anthropic.Anthropic()

tools = [
    {
        "name": "create_calendar_event",
        "description": "Create a calendar event with attendees and optional recurrence.",
        "input_schema": {
            "type": "object",
            "properties": {
                "title": {"type": "string"},
                "start": {"type": "string", "format": "date-time"},
                "end": {"type": "string", "format": "date-time"},
                "attendees": {
                    "type": "array",
                    "items": {"type": "string", "format": "email"},
                },
                "recurrence": {
                    "type": "object",
                    "properties": {
                        "frequency": {"enum": ["daily", "weekly", "monthly"]},
                        "count": {"type": "integer", "minimum": 1},
                    },
                },
            },
            "required": ["title", "start", "end"],
        },
    },
    {
        "name": "list_calendar_events",
        "description": "List all calendar events on a given date.",
        "input_schema": {
            "type": "object",
            "properties": {
                "date": {"type": "string", "format": "date"},
            },
            "required": ["date"],
        },
    },
]


def run_tool(name, tool_input):
    if name == "create_calendar_event":
        return {"event_id": "evt_123", "status": "created", "title": tool_input["title"]}
    if name == "list_calendar_events":
        return {"events": [{"title": "Existing meeting", "start": "14:00", "end": "15:00"}]}
    return {"error": f"Unknown tool: {name}"}


messages = [
    {
        "role": "user",
        "content": "Check what I have next Monday, then schedule a planning session that avoids any conflicts.",
    }
]

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=tools,
    messages=messages,
)

while response.stop_reason == "tool_use":
    # A single response can contain multiple tool_use blocks. Process all of
    # them and return all results together in one user message.
    tool_results = []
    for block in response.content:
        if block.type == "tool_use":
            result = run_tool(block.name, block.input)
            tool_results.append(
                {
                    "type": "tool_result",
                    "tool_use_id": block.id,
                    "content": json.dumps(result),
                }
            )

    messages.append({"role": "assistant", "content": response.content})
    messages.append({"role": "user", "content": tool_results})

    response = client.messages.create(
        model="claude-opus-4-6",
        max_tokens=1024,
        tools=tools,
        messages=messages,
    )

final_text = next(block for block in response.content if block.type == "text")
print(final_text.text)

# Ring 4: Error handling.
# Source for <CodeSource> in build-a-tool-using-agent.mdx.

import json

import anthropic

client = anthropic.Anthropic()

tools = [
    {
        "name": "create_calendar_event",
        "description": "Create a calendar event with attendees and optional recurrence.",
        "input_schema": {
            "type": "object",
            "properties": {
                "title": {"type": "string"},
                "start": {"type": "string", "format": "date-time"},
                "end": {"type": "string", "format": "date-time"},
                "attendees": {
                    "type": "array",
                    "items": {"type": "string", "format": "email"},
                },
                "recurrence": {
                    "type": "object",
                    "properties": {
                        "frequency": {"enum": ["daily", "weekly", "monthly"]},
                        "count": {"type": "integer", "minimum": 1},
                    },
                },
            },
            "required": ["title", "start", "end"],
        },
    },
    {
        "name": "list_calendar_events",
        "description": "List all calendar events on a given date.",
        "input_schema": {
            "type": "object",
            "properties": {
                "date": {"type": "string", "format": "date"},
            },
            "required": ["date"],
        },
    },
]


def run_tool(name, tool_input):
    if name == "create_calendar_event":
        if "attendees" in tool_input and len(tool_input["attendees"]) > 10:
            raise ValueError("Too many attendees (max 10)")
        return {"event_id": "evt_123", "status": "created", "title": tool_input["title"]}
    if name == "list_calendar_events":
        return {"events": [{"title": "Existing meeting", "start": "14:00", "end": "15:00"}]}
    raise ValueError(f"Unknown tool: {name}")


messages = [
    {
        "role": "user",
        "content": "Schedule an all-hands with everyone: " + ", ".join(f"user{i}@example.com" for i in range(15)),
    }
]

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=tools,
    messages=messages,
)

while response.stop_reason == "tool_use":
    tool_results = []
    for block in response.content:
        if block.type == "tool_use":
            try:
                result = run_tool(block.name, block.input)
                tool_results.append(
                    {"type": "tool_result", "tool_use_id": block.id, "content": json.dumps(result)}
                )
            except Exception as exc:
                # Signal failure so Claude can retry or ask for clarification.
                tool_results.append(
                    {
                        "type": "tool_result",
                        "tool_use_id": block.id,
                        "content": str(exc),
                        "is_error": True,
                    }
                )

    messages.append({"role": "assistant", "content": response.content})
    messages.append({"role": "user", "content": tool_results})

    response = client.messages.create(
        model="claude-opus-4-6",
        max_tokens=1024,
        tools=tools,
        messages=messages,
    )

final_text = next(block for block in response.content if block.type == "text")
print(final_text.text)

# Ring 5: The Tool Runner SDK abstraction.
# Source for <CodeSource> in build-a-tool-using-agent.mdx.

import json

import anthropic
from anthropic import beta_tool

client = anthropic.Anthropic()


@beta_tool
def create_calendar_event(
    title: str,
    start: str,
    end: str,
    attendees: list[str] | None = None,
    recurrence: dict | None = None,
) -> str:
    """Create a calendar event with attendees and optional recurrence.

    Args:
        title: Event title.
        start: Start time in ISO 8601 format.
        end: End time in ISO 8601 format.
        attendees: Email addresses to invite.
        recurrence: Dict with 'frequency' (daily, weekly, monthly) and 'count'.
    """
    if attendees and len(attendees) > 10:
        raise ValueError("Too many attendees (max 10)")
    return json.dumps({"event_id": "evt_123", "status": "created", "title": title})


@beta_tool
def list_calendar_events(date: str) -> str:
    """List all calendar events on a given date.

    Args:
        date: Date in YYYY-MM-DD format.
    """
    return json.dumps({"events": [{"title": "Existing meeting", "start": "14:00", "end": "15:00"}]})


final_message = client.beta.messages.tool_runner(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=[create_calendar_event, list_calendar_events],
    messages=[
        {
            "role": "user",
            "content": "Check what I have next Monday, then schedule a planning session that avoids any conflicts.",
        }
    ],
).until_done()

for block in final_message.content:
    if block.type == "text":
        print(block.text)