MCP Error Messages Written for Developers Hurt the Most Capable Agents Most
cs.SE, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-29
Code: https://github.com/WenJing95/tool-error-text
Sources
- The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF
- When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
- Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions
- From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agents
- Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy
- ToolMisuseBench: An Offline Deterministic Benchmark for Tool Misuse and Recovery in Agentic Systems
- ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
- Type-Error Ablation and AI Coding Agents
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties