Unverified50% confidenceFactExact time
在工具数量超过20个的场景下，工具描述的语义歧义度与模型选择准确率之间存在显著的负相关关系
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
VerifiedWhen available tools exceed 15-20, mainstream LLMs show a noticeable decline in tool selection accuracy.73% similarUnverifiedFew-shot提示通过提供2-5个示例让模型理解模式，比纯文字描述准确率通常高出20%-40%72% similarUnverified模型自主触发Skills时，全量注入所有Skill描述的方案在Skills数量超过数十个后性能显著下降68% similarUnverifiedIn an experiment where a tool returned 2 to the power of 8 as 200 (an incorrect answer), the model chose to trust its own knowledge (256) rather than the tool's returned result.68% similarUnverifiedResearch shows that high-quality prompts can bring a 20%–40% improvement in task completion rates compared to casually written prompts under the same model conditions.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/547370API
curl https://kongchang.com/api/v1/knowledge/claims/547370MCP
get_claim(id=547370)