Unverified60% confidenceFactTime unknown
OpenAI's Tool Calling protocol requires messages to strictly follow the paired order of assistant message → tool message, and each tool message must be precisely matched to the corresponding tool call request in the assistant message via tool_call_id.
2
Sources
60%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
LangChain AI Agent实战：流式输出+并行工具调用完整教程
youtubeJames Briggs
Related Entities
Related Claims
UnverifiedIn OpenAI's API specification, when the model decides to call a tool, the finish_reason field in the response is set to tool_calls, and the message object contains a tool_calls array, each element of which includes id, type, function.name, and function.arguments.80% similarUnverified在OpenAI和Anthropic的API设计中，每一次工具调用会产生至少两条新消息（调用请求+执行结果）79% similarUnverifiedThe OpenAI-compatible tool_calls schema has become a de facto standard, and orchestration frameworks such as LangChain, CrewAI, and LlamaIndex all parse tool calls based on it.76% similarUnverifiedThe APIs of vendors such as Anthropic and OpenAI have strict pairing requirements for message sequences: every tool_use returned by the model in the previous turn must have a corresponding tool_result in the next message, and a missing or out-of-order one will cause the entire request to be rejected.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16150API
curl https://kongchang.com/api/v1/knowledge/claims/16150MCP
get_claim(id=16150)