mlsanityData to 14 Oct 2026

Agentic DraCor and the Art of Docstring Engineering: Evaluating MCP-empowered LLM Usage of the DraCor API

arXiv 2508.13774 ↗First posted 19 Aug 2025cs.SE cs.AIcited by 0

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

Abstract (arXiv)

This paper reports on the implementation and evaluation of a Model Context Protocol (MCP) server for DraCor, enabling Large Language Models (LLM) to autonomously interact with the DraCor API. We conducted experiments focusing on tool selection and application by the LLM, employing a qualitative approach that includes systematic observation of prompts to understand how LLMs behave when using MCP tools, evaluating "Tool Correctness", "Tool-Calling Efficiency", and "Tool-Use Reliability". Our findings highlight the importance of "Docstring Engineering", defined as reflexively crafting tool documentation to optimize LLM-tool interaction. Our experiments demonstrate both the promise of agentic AI for research in Computational Literary Studies and the essential infrastructure development needs for reliable Digital Humanities infrastructures.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 2 of its 17 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

2 of 17 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models22 May

Other references · 1

  1. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 265

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
  2. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
  3. 2025MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use
  4. 2025Tool Preferences in Agentic LLMs are Unreliable
  5. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
  6. 2025MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
  7. 2025MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
  8. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations