Unverified50% confidenceFactExact time
Large language models treat tool descriptions as part of the system prompt during inference, so malicious instructions often receive a priority similar to that of normal instructions.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn 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.79% similarUnverifiedWhen a large language model calls tools, it needs to place the names, descriptions, and parameter schemas of all available tools into the context, from which the model selects the most appropriate one during inference.78% similarUnverified语言模型对工具输出有一定判断力，外部知识与模型内部信念的偏差程度越大模型越不相信78% similarVerifiedThe tool-calling mechanism allows large language models to dynamically invoke external functions during inference, representing a fundamental leap from language models to action models.77% similarVerifiedDuring inference, large models read tool metadata as context and use semantic understanding to determine whether a tool needs to be called and what parameters to pass, a process known as Function Calling or Tool Use.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1056047API
curl https://kongchang.com/api/v1/knowledge/claims/1056047MCP
get_claim(id=1056047)