Tool Use

Function Calling (Tool Use) is a standardized mechanism for large models to invoke external tools, where developers pre-declare tool names, descriptions, and parameter schemas, and the model autonomously determines when to make a call.

The underlying mechanism of Tool Use is that developers pre-define the name, description, and parameter structure (Schema) of tools, and the model determines during inference when and which tool to call and outputs structured invocation instructions.

The tool-calling (Function Calling) mechanism allows the model to invoke external tools during reasoning, such as file read/write operations, terminal commands, and search APIs.

AI Agent通过工具调用（Tool Use）机制与外部系统交互，包括执行代码、调用API、读写数据库等

Anthropic and OpenAI successively released models supporting tool use and multi-step reasoning around 2024.

Tool-Augmented AI is an important development direction for current large model applications, with mechanisms such as OpenAI's Function Calling and Anthropic's Tool Use underpinning this paradigm at the foundational level.

Function Calling机制中，开发者将工具的名称、功能描述、参数Schema（通常为JSON Schema格式）注入到模型的请求中，模型输出结构化的JSON而非自然语言来调用工具

Anthropic introduced Tool Use in Claude, and Google provides a capability similar to Function Calling in Gemini.

Anthropic introduced Tool Use as its Function Calling solution.

Function calling (tool calling) refers to the ability of a large language model to proactively request the invocation of external functions or APIs during the generation of a response.

The basic principle of tool calling is that the model identifies scenarios requiring external capabilities, outputs a structured function call request (usually in JSON format), and after the external system executes it, the result is returned to the model to continue reasoning.

Research indicates that models may produce unfaithful chains of thought, where the surface-level reasoning steps are inconsistent with the actual basis for decision-making.

The operation of AI Agents relies on large language model APIs, vector databases, tool-calling interfaces, third-party SDKs, and various rapidly iterating frameworks, resulting in an extremely long execution chain

Coding Agent与普通AI聊天机器人的本质区别在于工具调用（Tool Use）能力，包括执行终端命令、读写文件系统、调用API等

Tool calling allows models to dynamically invoke external functions during inference and incorporate execution results into the context of subsequent reasoning, forming a closed loop of perception, decision-making, and execution.

AI Agents interact with external tools through standardized interfaces (such as OpenAI's Function Calling and Anthropic's Tool Use protocol), and CLI command-line tools are naturally suited to this invocation pattern.

During inference, large models read tool metadata as context and use semantic understanding to determine whether a tool needs to be called and what parameters to pass, a process known as Function Calling or Tool Use.

Without tool-calling capability, large language models can only operate within the language space and cannot truly affect external systems.

Agent mode is implemented through a 'tool-calling' mechanism, whereby the model can autonomously decide to call external APIs, execute shell commands, read and write files, or browse the web.

Different models use different function-calling formats: OpenAI uses the tools parameter, Anthropic uses tool_use blocks, and open-source models each have their own template formats.