<essential_principles>

WebMCP is a browser-native standard that exposes structured tools for AI agents on websites. Instead of screen-scraping, agents interact through typed JavaScript APIs and HTML annotations.

Two APIs:

• Imperative API — window.navigator.modelContext — register tools via JavaScript
• Declarative API — HTML toolname/tooldescription attributes on <form> elements

Prerequisites: Chrome 146.0.7672.0+, chrome://flags/#enable-webmcp-testing enabled.

Core principles that always apply:

1. Tools must be atomic and composable — one function per tool, no overlapping tools with nuanced differences. Combine similar tools into one with input parameters.

2. Accept raw user input — tools should accept natural strings (e.g., "11:00") not computed values (e.g., minutes-from-midnight). Minimize cognitive computing for the model.

3. Validate in code, not schema — schema constraints are helpful but not guaranteed. Validate within execute functions and return descriptive errors so agents can self-correct.

4. Update UI before returning — agents use UI state to verify execution. Ensure execute/submit logic updates visible state before resolving.

5. Positive, verb-first descriptions — describe what the tool does and when to use it. Avoid negations. "Creates a calendar event for a specific date" not "Do not use for weather."

</essential_principles>

1. Set up WebMCP in a project (initial integration)
2. Add a tool using the imperative JavaScript API
3. Add a tool using the declarative HTML form API
4. Debug WebMCP tools that aren't working
5. Audit existing WebMCP implementation for best practices
6. Test WebMCP tools
7. Something else

Wait for response before proceeding. </intake>

After reading the workflow, follow it exactly. </routing>

<reference_index>

All in references/:

APIs: imperative-api.md, declarative-api.md Design: tool-design.md Events: events-and-css.md Quality: testing.md, anti-patterns.md

</reference_index>

<workflows_index>

All in workflows/:

</workflows_index>

<templates_index>

All in templates/:

</templates_index>

<verification_loop>

After every WebMCP change:

1. Open Chrome DevTools console — check for JS errors
2. Verify navigator.modelContext exists (Chrome flag enabled?)
3. Use Model Context Tool Inspector extension to list registered tools
4. Manually execute a tool from the inspector to confirm it works
5. Check that UI updates are visible after tool execution

Report to user:

• "Tools registered: X imperative, Y declarative"
• "Tool [name]: executes successfully / returns error [detail]"
• "UI state: updates correctly after execution / missing update"

</verification_loop>