# Your tools work. Will the agent use them right?

DevFeed: [Your tools work. Will the agent use them right?](<https://devfeed.tech/articles/your-tools-work-will-the-agent-use-them-right-9224.md>)

Original publisher: [Read original article](<https://webflowmarketingmain.com/blog/mcp-eval-harness>)

Author: Gil Levin

Published: 2026-09-10T00:00:00Z

Content type: article

Language: en

Sources: [Webflow Blog](<https://devfeed.tech/sources/webflow-blog.md>)

Topics: [Model Context Protocol (MCP)](<https://devfeed.tech/topics/model-context-protocol-mcp.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [tools](<https://devfeed.tech/tags/tools.md>)

## AI overview

Webflow's MCP eval harness tests whether autonomous agents use its tools correctly to complete plain-English, multi-step tasks. It runs Claude Code or OpenAI's Codex CLI against disposable Webflow sites, combines deterministic checks with LLM and visual judging, and sends traces and scores to Datadog.

## Source excerpt

A passing MCP tool test tells you the JSON is valid. It doesn't tell you an agent will pick the right tool, in order, and get the task right.