Unverified50% confidenceFactExact time
Different frameworks define tool-calling formats differently (OpenAI format, Anthropic format, Ollama's own format), and models not trained for a specific format will produce malformed calls.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedDifferent models use different function-calling formats: OpenAI uses the tools parameter, Anthropic uses tool_use blocks, and open-source models each have their own template formats.78% similarUnverifiedOpenAI's and Anthropic's Tool Use protocol formats are not compatible with each other, and best practices for system prompts also differ.72% similarUnverified开放权重模型的工具调用格式往往不如闭源模型稳定，闭源模型通过大量RLHF、后训练对齐和运行时约束（如JSON Mode、Structured Output）确保工具调用格式精确性72% similarUnverifiedMany providers (including OpenAI) explicitly require that tool definitions carry the additionalProperties: false field in order to enable strict-mode structured output.70% similarUnverifiedOpenAI、Anthropic和Google的大模型对Tool Calling的描述格式要求各不相同，存在碎片化问题69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977879API
curl https://kongchang.com/api/v1/knowledge/claims/977879MCP
get_claim(id=977879)