Unverified50% confidenceDecision RuleExact time
When handing the schema to the model, if the model is responsible for producing the raw input, `io: "input"` should be used.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDuring inference, the model receives a metadata list of all registered tools, and the tool description text is directly incorporated into the model's reasoning context.68% similarUnverifiedPrompt injection attempts to override the system prompt and induce the model to perform unauthorized actions by embedding malicious instructions into external content processed by the model, and is logically analogous to SQL injection.66% similarUnverifiedOutput guardrails are check logic executed after the model generates content and before it is returned to the user, used to handle the risk that the model may say anything, with common implementations being regex matching or lightweight classifiers.66% similarUnverified掌握工作流逻辑的核心在于理解每个节点的「输入→处理→输出」基本模型66% 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.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1040207API
curl https://kongchang.com/api/v1/knowledge/claims/1040207MCP
get_claim(id=1040207)