mlsanityData to 7 Oct 2026

DADL: A Declarative Description Language for Enterprise Tool Libraries in LLM Agent Systems

arXiv 2605.05247 ↗First posted 4 May 2026cs.SEcited by 0

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

The Model Context Protocol (MCP) is the standard interface between large language model (LLM) agents and external tools. At organizational scale, however, it exposes two structural problems. First, every API integration is shipped as a dedicated server process with its own deployment, dependency tree, and credential handling; recent empirical work shows the overwhelming majority of these servers are thin wrappers around REST APIs. Second, the per-tool registration model causes context window consumption to grow linearly with catalog size, forcing real deployments to expose only a small fraction of the APIs an organization actually uses. We present DADL (Dunkel API Description Language), a YAML format describing a REST API's endpoints, authentication, pagination, response shaping, and access classification in a single declarative file. A DADL file is interpreted by an execution layer at runtime; no per-API server process is deployed and no integration code is generated, though the runtime is itself a server. Because all tools share that runtime, credentials and authorization are managed centrally, and the catalog reaches the LLM through a fixed-size Code Mode interface independent of size. The result is an Enterprise Tool Library: a versioned, auditable collection of API integrations any team can extend, share, and consume through one authentication and authorization boundary. The DADL v0.1 specification is released under CC BY-SA 4.0, and a public registry contains 1,833 tool definitions across 20 services. On this catalog, Code Mode reduces the context cost of tool advertisement from approximately 142,000 tokens to approximately 1,000, a 142x reduction; the per-call cost of search and execute invocations is additional and depends on the task.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 7 of its 13 references that are in the map. First posted on arXiv 4 May 2026.

Builds on

7 of 13 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations29 Jul

Other references · 6

  1. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
  2. 2025Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Serverscited by 62
  3. 2025MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploitscited by 61
  4. 2025From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agentscited by 14
  5. 2025ToolFactory: Automating Tool Generation by Leveraging LLM to Understand REST API Documentationscited by 8
  6. 2025MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Serverscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Framework for Testing and Adapting REST APIs as LLM Tools
  2. 2025A Declarative Language for Building And Orchestrating LLM-Powered Agent Workflows
  3. 2025Automated Creation and Enrichment Framework for Improved Invocation of Enterprise APIs as Tools
  4. 2026Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System
  5. 2026Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
  6. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
  7. 2025In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents
  8. 2026Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance