Unverified50% confidenceOpinionExact time
Too many tools cause model selection confusion; the current mainstream direction is to provide a small number of tools and let the model iteratively leverage them on its own, or let the model dynamically design tools based on the task (especially by writing scripts).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/15/2026
First Seen
Valid until: 12/14/2026
Sources
Related Entities
Related Claims
UnverifiedThe same model can perform very differently across different tools; the model determines the system's lower bound while the Harness determines the upper bound of agent performance.78% similarUnverifiedThe quality of support for Tool Use/Function Calling varies enormously across different models, and many open-source models perform inconsistently in multi-turn tool calls and complex parameter parsing.78% similarUnverified工具可分为「补偿智能不足的工具」和「随智能增长的工具」，前者会强迫特定写代码顺序且无法随模型变强受益，后者随模型越强越有用76% similarUnverifiedLarge models are continuously internalizing capabilities that previously required external tools; for example, computational functions that once required dedicated plugins have now become built-in model capabilities.75% similarUnverifiedTool的语言驱动工具选择机制让工具开发与模型训练解耦，开发者无需重新训练模型只需注册新工具即可扩展Agent能力73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/923461API
curl https://kongchang.com/api/v1/knowledge/claims/923461MCP
get_claim(id=923461)