Expired50% confidenceFactExact time
The core idea of the Tool Use protocol is to completely decouple decision-making from execution: the model is only responsible for reasoning and planning and outputting JSON, while actual file reading/writing and command execution are handled by the local runtime.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Claude Code Architecture Deep Dive: ReAct Loop, Context Window & CLAUDE.md Mechanism Explained
bilibiliData老毕6/17/2026
Related Claims
UnverifiedTool Use (function calling) allows LLMs to invoke external tools during inference, such as reading files, performing searches, calling APIs, or executing code.78% similarPartially VerifiedThe tool-calling (Function Calling) mechanism allows the model to invoke external tools during reasoning, such as file read/write operations, terminal commands, and search APIs.73% similarUnverifiedTool Calling (Function Calling) allows an LLM to dynamically invoke external APIs, database queries, and code execution tools during the reasoning process69% similarUnverified工具是模型可运行的函数，资源是只读数据且无副作用，提示词是用户主动选择的可复用模板69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/45041API
curl https://kongchang.com/api/v1/knowledge/claims/45041MCP
get_claim(id=45041)