Unverified50% confidenceFactExact time
Tool Use协议的核心思想是将决策与执行完全解耦：模型只负责推理规划并输出JSON，实际文件读写和命令执行由本地运行时处理
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
UnverifiedTool Use（函数调用）允许LLM在推理过程中调用外部工具，如读取文件、执行搜索、调用API或运行代码78% similarPartially Verified工具调用（Function Calling）机制允许模型在推理过程中调用外部工具，如文件读写、终端命令、搜索 API73% similarUnverifiedTool Calling (Function Calling) allows an LLM to dynamically invoke external APIs, database queries, and code execution tools during the reasoning process69% similarUnverified工具是模型可运行的函数，资源是只读数据且无副作用，提示词是用户主动选择的可复用模板69% similarUnverified在Tool Use场景中，系统需在运行时将可用工具的Schema、权限范围和调用格式动态插入上下文68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/45041API
curl https://kongchang.com/api/v1/knowledge/claims/45041MCP
get_claim(id=45041)