Skip to main content
Glama

verify_ui

Judge a screenshot of the running UI. Paid.

You drive the browser; verifAIed judges what you got. Take a screenshot of the change you just made, say what it was supposed to do, and this returns a verdict — plus records it, so check_done can hold the branch to it.

Two modes:

  • With intent (recommended): checks one claim. "The error state now shows a Retry button" → pass / fail / unclear, with a confidence and the reasoning. unclear is a real answer, used when the screenshot doesn't show the region the claim is about — treat it as "screenshot the right thing and ask again", not as a pass.

  • Without intent: a rubric review (layout, hierarchy, legibility, consistency, obvious broken state) returning clean or issues with a defect list.

target attaches the verdict to one component as path/to/File.tsx::ComponentName, which is what clears that component's visually_unreviewed gap. A target that doesn't resolve is not an error: the verdict is still recorded against the branch and the response carries a warning saying so.

screenshot_base64 is the raw image bytes, base64-encoded (a data: URL prefix is fine). PNG, JPEG, GIF or WebP; a viewport-sized capture is plenty and anything over ~1.5MB of base64 is rejected with a resize hint. Pass console_errors when you have them — a visual defect and a console error are very often the same bug.

The screenshot is stored as session evidence: each call opens a one-moment session in the branch's ledger and attaches the image to it, so the Tests page can show the frame the verdict was about. The reasoning text is still the record — the picture is the receipt.

Failing an intent check creates an intent_mismatch gap; a changed component with no verdict creates visually_unreviewed. Both activate only once this branch has at least one verdict, so a repo that doesn't use this tool never sees them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "repository": "<repository>",
      "screenshot_base64": "<screenshot_base64>"
    },
    "name": "verify_ui"
  }
}

Input Schema

NameRequiredDescriptionDefault
branchNo
intentNo
targetNo
viewportNo
repositoryYes
console_errorsNo
screenshot_base64Yes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the whole load, and it does so well: it discloses that the tool is paid, that the screenshot is persisted as session evidence in a ledger, that base64 over ~1.5MB is rejected with a resize hint, and that an unresolved `target` yields a warning rather than an error. The only undisclosed behaviors are the concrete failure/rate-limit or auth mechanics of the paid call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then cleanly sectioned into modes, target behavior, encoding limits, and gap side effects. A few lines are rhetorical rather than informational ('the picture is the receipt'), but nearly every sentence carries a fact an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a seven-parameter, no-output-schema tool, the description supplies return shapes for both modes (`pass`/`fail`/`unclear` with confidence and reasoning; `clean`/`issues` with a defect list) plus the downstream gap effects (`intent_mismatch`, `visually_unreviewed`) and their activation condition. An agent has everything needed to invoke and interpret it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage the description must compensate, and it does for most parameters: `intent`'s two modes and verdict vocabulary, `target`'s `path/to/File.tsx::ComponentName` format and non-resolving behavior, `screenshot_base64`'s encoding/formats/size limit, and `console_errors`' purpose. `viewport` and `repository` are never explained, leaving two of seven parameters undocumented anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening line states a specific verb and resource: 'Judge a screenshot of the running UI.' It immediately frames the division of labor ('You drive the browser; verifAIed judges what you got') and names the downstream sibling 'check_done', so an agent can place it among the other tools without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly contrasts the two operating modes (with `intent` recommended vs. without `intent` for a rubric review), tells the agent when to pass `console_errors` and a `target`, and even instructs how to interpret `unclear` ('screenshot the right thing and ask again, not as a pass'). This is when-to-use and how-to-interpret guidance in full.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources