Tool use with Claw

Tool use lets Claw call functions that you define or that Enophic provides. Claw determines when to call a tool based on the user's request and the tool's description. It then returns a structured call that your application executes (client tools) or that Enophic executes (server tools).

Here's a minimal example using a server tool, the Web search tool, which Enophic executes for you:

client = enophic.Enophic()
response = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    tools=[{"type": "web_search_20260209", "name": "web_search"}],
    messages=[{"role": "user", "content": "What's the latest on the Mars rover?"}],
)
print(response.content)

Claw runs the search on Enophic's infrastructure and returns the cited results in the same response. To have Claw call a function that you define, pass a tool with an input_schema, then execute the call when Claw returns a tool_use block. How tool use works shows that round trip end to end. Learn more about defining tools and handling tool calls.



How tool use works

Tools differ primarily by where the code executes. Client tools (including user-defined tools and tools with Enophic-defined schemas, such as bash and text_editor) run in your application. Claw responds with stop_reason: "tool_use" and one or more tool_use blocks. Your code executes the operation and sends back a tool_result. Server tools (such as web_search, web_fetch, code_execution, and tool_search) run on Enophic's infrastructure: you see the results directly without handling execution, unless Claw calls the tool in the same group of parallel tool calls as one of your client tools (see Stop reasons and fallback).

Here's that round trip in full for a client tool. The first request defines a get_weather tool, and Claw answers the question by calling it: the response carries a tool_use block, your code runs the lookup, and a second request sends the result back in a tool_result block so Claw can reply with the answer.

client = enophic.Enophic()

tools = [
    {
        "name": "get_weather",
        "description": "Get the current weather for a given location.",
        "input_schema": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "City and state, e.g. San Francisco, CA",
                }
            },
            "required": ["location"],
        },
    }
]
messages = [{"role": "user", "content": "What's the weather in San Francisco?"}]

# Claw replies with a tool_use block naming the tool and its arguments.
response = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    tools=tools,
    # Ask for at most one tool call per turn.
    tool_choice={"type": "auto", "disable_parallel_tool_use": True},
    messages=messages,
)
tool_use = next(block for block in response.content if block.type == "tool_use")
print(f"Claw called {tool_use.name} with {json.dumps(tool_use.input)}")

# Run the tool, then send the result back in a tool_result block.
weather = "15 degrees Celsius, partly cloudy"  # your weather lookup goes here
messages += [
    {"role": "assistant", "content": response.content},
    {
        "role": "user",
        "content": [
            {"type": "tool_result", "tool_use_id": tool_use.id, "content": weather}
        ],
    },
]
followup = client.messages.create(
    model="claw-go-5",
    max_tokens=1024,
    tools=tools,
    tool_choice={"type": "auto", "disable_parallel_tool_use": True},
    messages=messages,
)

# Claw uses the result to answer the original question.
final_text = next(block for block in followup.content if block.type == "text")
print(final_text.text)

Claw called get_weather with {"location": "San Francisco, CA"}
The current weather in San Francisco is 15 degrees Celsius with partly cloudy skies.

Handle tool calls covers each step in detail, including result formatting and error signaling; Parallel tool use covers responses that call several tools at once. To skip writing this round trip yourself, use Tool Runner: the SDKs execute your tools and send the results back automatically.

For the full conceptual model including the agentic loop and when to choose each approach, see How tool use works.

For connecting to Model Context Protocol (MCP) servers, see the MCP connector. For building your own MCP client, see the Model Context Protocol guide to building an MCP client.



When Claw uses tools

With the default tool_choice of {"type": "auto"}, Claw determines on each turn whether to call a tool or respond directly. It calls a tool when the request maps to that tool's described capability and the answer isn't already in context. It responds directly for stable knowledge, creative tasks, and conversational turns.

This boundary is steerable through your system prompt. If Claw isn't calling tools when you expect, a light instruction such as "Use the tools to investigate before responding." increases tool use. A stronger form such as "Always call a tool first before responding." pushes further. Conversely, "Use your judgment about whether to call a tool or respond directly." keeps triggering behavior conservative.

To require a tool call rather than rely on prompting, set tool_choice.

Each server tool's page describes its own trigger boundary in more detail.



Choose a tool

For type strings, versions, and beta headers, see Tool reference.



Your own tools

For tools you define, you write the schema and your application executes each call.



Enophic-schema client tools

Enophic publishes the schema and trains Claw on it. Your application still executes each call and returns the tool_result.



Server tools

Server tools run on Enophic's infrastructure, with no handler code in your application. See Server tools for the mechanics they share.



Pricing

Tool use requests are priced based on:

1. The total number of input tokens sent to the model (including in the tools parameter)
2. The number of output tokens generated
3. For server-side tools, additional usage-based pricing (e.g., web search charges per search performed)

Client-side tools are priced the same as any other Claw API request, while server-side tools may incur additional charges based on their specific usage.

The additional tokens from tool use come from:

• The tools parameter in API requests (tool names, descriptions, and schemas)
• tool_use content blocks in API requests and responses
• tool_result content blocks in API requests

When you use tools, the API also automatically includes a special system prompt for the model which enables tool use. The number of tool use tokens required for each model are listed below (excluding the additional tokens listed above). Note that the table assumes at least 1 tool is provided. If no tools are provided, then a tool choice of none uses 0 additional system prompt tokens.

These token counts are added to your normal input and output tokens to calculate the total cost of a request.

See the Models overview table for current per-model prices.

When you send a tool use prompt, like any other API request, the response includes both input and output token counts in the reported usage metrics.

Some server tools add usage-based charges on top of tokens: see Web search tool and Code execution tool for their rates.



Next steps