Unverified60% confidenceFactExact time
A language model never calls tools directly; it only outputs a piece of text stating which tool it wants to call, after which code executes the call and returns the result as text.
2
Sources
60%
Confidence
Long-term
Relevance
9/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLarge language models do not execute code themselves; they are only responsible for calling tools, while the application-layer code actually executes the functions.80% similarUnverified模型调用工具时会将输出从普通文本切换为结构化的函数调用格式（finish_reason: tool_calls）77% similarUnverifiedThe language model receives a single flat stream of text containing the system prompt, user messages, retrieved documents and tool return results, with no reliable way to distinguish instructions from ordinary content.76% similarUnverified提示词工程无需修改模型权重，仅凭文本指令即可实现任务切换74% similarUnverifiedThe model marked as coder outputs fabricated <tool> blocks as plain text rather than executing real tool calls, resulting in no disk changes.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/953110API
curl https://kongchang.com/api/v1/knowledge/claims/953110MCP
get_claim(id=953110)