Unverified50% confidenceFactExact time
The embedding model concatenates a tool's name, function description, parameter descriptions, and so on, and maps them into a fixed-dimensional vector; when a task arrives, the cosine similarity between the task vector and each tool vector can be computed to rank and recall.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe tool definitions themselves also consume context tokens, and the model's understanding of a tool depends on the clarity of its description.78% similarVerifiedThe key breakthrough in tool-calling capability lies in the model's ability to generate structured function-call requests and correctly parse tool return results before continuing to reason, rather than simply concatenating tool outputs into the prompt77% similarUnverifiedThe accuracy of tool calling depends on the model's understanding of the task and the clarity of the tool descriptions.77% similarUnverifiedThe second step is the host injecting the tool description text into the model's context; the model's entire knowledge of the tool comes only from this description.76% similarUnverifiedSkill机制通过在上下文中注入结构化的Markdown指令引导模型完成特定任务，无需对模型本身进行微调74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1110480API
curl https://kongchang.com/api/v1/knowledge/claims/1110480MCP
get_claim(id=1110480)