Unverified50% confidenceFactExact time
工具调用中模型本身不执行代码，只负责决策调用哪个工具，真正的执行权留在开发者控制的宿主程序中
1
Sources
50%
Confidence
Long-term
Relevance
9/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn Claude Code's architecture, the model cannot directly execute tool operations; it can only return instructions to the harness for processing.71% similarUnverifiedIn Tool Calling, the LLM itself does not execute functions — it returns a call intent, and the application layer code actually executes it and passes the result back to the model68% similarUnverified开发者不应从零手写LangChain或Claude SDK这类框架，应直接应用现成框架而非重复造轮子68% similarUnverified开发者应坚持理解每一行提交的代码，如果无法解释一段代码为何这样写、在什么条件下会失效，就不应将其纳入生产系统67% similarUnverifiedSkill Creator eliminates the need for users to manually write Skill definition files, configure parameters, and write execution scripts.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/927014API
curl https://kongchang.com/api/v1/knowledge/claims/927014MCP
get_claim(id=927014)