Unverified50% confidenceFactExact time
This version supports defining scoring criteria (rubrics) using structured JSON, rather than writing evaluation criteria into natural language prompts
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
UnverifiedTool-calling standards have gradually coalesced into a de facto standard of describing tools with JSON Schema and passing call results via structured messages.73% similarUnverifiedJSON Mode only guarantees that the output is valid JSON without constraining the field structure; Structured Outputs enforces output conforming to a predefined JSON Schema at the syntactic level by applying a finite state machine (FSM) to constrain the token sampling path during the decoding phase.71% similarUnverifiedFSM constraints can guarantee JSON format validity at the grammatical level, but cannot constrain the semantic quality of fields.70% similarUnverified在FastMCP中，函数的类型提示和文档字符串会自动转换为符合JSON Schema规范的工具模式，无需手写JSON Schema69% similarUnverifiedStructured output constrains format via JSON Schema, which can eliminate randomness at the format level and confine uncertainty to the scope of semantic content.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/927294API
curl https://kongchang.com/api/v1/knowledge/claims/927294MCP
get_claim(id=927294)