Unverified50% confidenceFactExact time
When an LLM decides to call a tool, it reads the JSON Schema description rather than the function source code, and the model cannot see the Python implementation details.
1
Sources
50%
Confidence
Long-term
Relevance
9/26/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn the tool-calling mechanism, developers attach a tool description list in JSON Schema format when calling the LLM API, and the model outputs call parameters in structured JSON format80% similarUnverifiedLLM本身并不直接执行工具，而是生成一个JSON字符串指定要调用的工具名和参数，由Agent执行逻辑解析并实际调用对应函数79% similarUnverifiedThe tool-calling capability of a large model itself actually only outputs a structured piece of JSON data describing which function to call and what parameters to pass; the model itself has no ability to execute code.75% similarUnverifiedThe JSON structure returned by LLM APIs may vary across model versions.72% similarVerifiedThe Function Calling mechanism allows LLMs to declare in structured JSON format the external tools and parameters they need to invoke, and the tool's return value is injected as-is into the next round of model input.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/952345API
curl https://kongchang.com/api/v1/knowledge/claims/952345MCP
get_claim(id=952345)