Unverified95% confidenceFactTime unknown
LLM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
1
Sources
95%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn 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 format84% similarUnverifiedThe Function Calling mechanism allows LLMs to declare in structured JSON format the external tools and parameters they need to invoke, and the tool's return value is injected as-is into the next round of model input.81% similarUnverifiedUnder 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.79% 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.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16110API
curl https://kongchang.com/api/v1/knowledge/claims/16110MCP
get_claim(id=16110)