Unverified50% confidenceFactExact time
The tool-calling capability of a large model itself actually only outputs a structured piece of JSON data describing which function to call and what parameters to pass; the model itself has no ability to execute code.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedUnder the tool-calling paradigm, the LLM outputs a structured function-call intent (in JSON format), which is actually executed by an external system that returns the result to the model.76% similarUnverifiedLLM本身并不直接执行工具，而是生成一个JSON字符串指定要调用的工具名和参数，由Agent执行逻辑解析并实际调用对应函数76% similarUnverifiedTools are essentially function wrappers for external capabilities, paired with JSON Schema descriptions that enable the model to understand a tool's functionality and parameter format.75% similarVerifiedFunction 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75% similarUnverifiedIn the tool-calling mechanism, developers attach a tool description list in JSON Schema format when calling the LLM API, and the model outputs call parameters in structured JSON format75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/897085API
curl https://kongchang.com/api/v1/knowledge/claims/897085MCP
get_claim(id=897085)