Unverified50% confidenceFactExact time
客户端拿到工具执行结果后需构造role为tool的消息，携带对应的tool_call_id和执行结果回传给模型
1
Sources
50%
Confidence
Long-term
Relevance
8/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen an LLM model decides to call a tool, it generates an assistant message containing a tool_use block; after the tool finishes executing, the result is appended as a new message in tool_result format78% similarUnverified在LangChain框架中，Tool调用结果通过ToolMessage对象追加到消息链75% 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 API74% similarUnverified当模型输出工具调用语法后会停止响应，Harness执行工具并将输出追加到对话历史末尾，然后向同一模型重新发起请求73% similarUnverified在Agent Scratchpad中，LLM生成的工具调用作为AI Message存储，工具返回的结果作为Tool Message存储，两者通过tool_call_id进行关联72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/826200API
curl https://kongchang.com/api/v1/knowledge/claims/826200MCP
get_claim(id=826200)