Verified65% confidenceFactExact time
The model decides when to invoke tools, the client or user chooses which resources to read, and prompts are usually triggered explicitly by the user; this division shapes permission design.
3
Sources
65%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
Unverified该工具提供Token用量查看功能，用户需自行配置对话模型和生图模型79% similarUnverified工具是模型可运行的函数，资源是只读数据且无副作用，提示词是用户主动选择的可复用模板77% similarUnverifiedWhen an application sends a user request to the model, it includes a list of tools the model can use, with each tool having a name and an input schema.77% similarUnverifiedThe actual number of tokens consumed by a single user request includes the entire input context (including conversation history, system prompts, tool definitions, etc.) as well as the response content generated by the model.77% similarUnverifiedUser behavior modeling dynamically adjusts model outputs by analyzing implicit signals such as users' task choices, modification behavior, and expression style.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062581API
curl https://kongchang.com/api/v1/knowledge/claims/1062581MCP
get_claim(id=1062581)