Verified65% confidenceFactExact time
When available tools exceed 15-20, mainstream LLMs show a noticeable decline in tool selection accuracy.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Core Analysis of Agent Skill: Progressive Disclosure & Middleware Practical Guide
bilibili码士集团-马小雪6/22/2026
Related Claims
Unverified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73% 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63% similarUnverified学术研究表明，当误报率超过30%时，开发者对工具的信任度和使用意愿会显著下降62% similarUnverified大模型的性能提升已经明显放缓，最近新版本的评分甚至不一定超越之前的模型，能力基本已定型61% similarUnverifiedGoogle内部研究显示，当工具误报率超过10%时，开发者的采纳率会急剧下降61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/42523API
curl https://kongchang.com/api/v1/knowledge/claims/42523MCP
get_claim(id=42523)