Expired50% confidenceFactTime unknown
When 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 format
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
SubAgent Architecture: The Core Implementation for Context Isolation
bilibili日新月异max
Related Claims
Unverified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76% similarUnverifiedTool Calling (Function Calling) allows an LLM to dynamically invoke external APIs, database queries, and code execution tools during the reasoning process76% similarUnverifiedTool Use (function calling) allows LLMs to invoke external tools during inference, such as reading files, performing searches, calling APIs, or executing code.74% similarUnverifiedLLM 0.32a0 built the tool-call loop into the library via the execute_tool_calls() and reply() methods.74% 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73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/56417API
curl https://kongchang.com/api/v1/knowledge/claims/56417MCP
get_claim(id=56417)