Unverified50% confidenceDecision RuleExact time
The inputs to tool functions come from model generation and must be treated as untrusted input.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Claims
UnverifiedWhen calling tools, models sometimes generate malformed parameters, call nonexistent functions, or fall into infinite loops; mature agent frameworks incorporate parameter validation, retry limits, and exception-handling mechanisms.77% similarUnverifiedIn tool-calling scenarios, a model's selection between functionally similar tools is highly dependent on the clarity of the input signal, rather than hard-coded routing rules.74% similarUnverifiedWhen the model requests a tool call, the finish_reason field in the response has the value tool_calls rather than stop, which is the standard signal for determining whether the model is requesting a tool call.73% similarUnverified函数调用中模型本身无法主动执行代码，仅识别意图并生成符合函数签名的结构化参数，实际执行由调用方负责71% similarVerifiedThe basic principle of tool calling is that the model identifies scenarios requiring external capabilities, outputs a structured function call request (usually in JSON format), and after the external system executes it, the result is returned to the model to continue reasoning.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023172API
curl https://kongchang.com/api/v1/knowledge/claims/1023172MCP
get_claim(id=1023172)