Automated Creation and Enrichment Framework for Improved Invocation of Enterprise APIs as Tools

2025-09-15

AI Summary

Enterprise API documentation is often incomplete, interfaces are complex, and tool suites are large-scale—leading to difficulties in LLM agent tool selection and a 25% drop in payload generation accuracy. To address this, we propose ACE, the first framework enabling end-to-end automatic construction of LLM-callable tools from enterprise APIs. ACE introduces three core techniques: parameter-aware enhanced tool description generation, context-aware example injection, and runtime shortlist dynamic filtering—collectively reducing prompt engineering complexity. Crucially, ACE requires no human annotation, supports both private and open-source APIs, and integrates seamlessly with mainstream agent frameworks (e.g., LangChain, LlamaIndex). Extensive experiments demonstrate a 25% improvement in tool-calling accuracy and strong generalization and scalability across complex enterprise scenarios.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Prompt Engineering / Prompting
• Multiagent Systems: Agent Communication

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recent advancements in Large Language Models (LLMs) has lead to the development of agents capable of complex reasoning and interaction with external tools. In enterprise contexts, the effective use of such tools that are often enabled by application programming interfaces (APIs), is hindered by poor documentation, complex input or output schema, and large number of operations. These challenges make tool selection difficult and reduce the accuracy of payload formation by up to 25%. We propose ACE, an automated tool creation and enrichment framework that transforms enterprise APIs into LLM-compatible tools. ACE, (i) generates enriched tool specifications with parameter descriptions and examples to improve selection and invocation accuracy, and (ii) incorporates a dynamic shortlisting mechanism that filters relevant tools at runtime, reducing prompt complexity while maintaining scalability. We validate our framework on both proprietary and open-source APIs and demonstrate its integration with agentic frameworks. To the best of our knowledge, ACE is the first end-to-end framework that automates the creation, enrichment, and dynamic selection of enterprise API tools for LLM agents.

Problem

• Automates transformation of enterprise APIs into LLM-compatible tools
• Improves tool selection accuracy and payload formation for LLMs
• Reduces prompt complexity while maintaining system scalability

Innovation

• Generates enriched API tool specifications
• Incorporates dynamic shortlisting mechanism
• Automates enterprise API transformation for LLMs