Skip to main content
Glama

UI Verify

by io.github.igrlk

Fetch the actual pixels of a story image

render_diff_image
Read-only

Fetch a story's image as an INLINE image (base64 pixels, not a URL) so a vision model can look at it directly. Needs a native MCP client that renders image content; piped through raw curl it is useless (use get_diff's URLs there instead). Two ways to address it: (1) diffResultId + which for a CHANGED story - which is baseline|candidate|diff (the triptych) or before_after, the baseline and candidate SIDE BY SIDE (before on the left, after on the right) cropped to the changed region - and when a story changed in SEVERAL far-apart places, one such crop PER region stacked top to bottom, so a header-plus-footer change is two tight crops, not a page-tall image. before_after is usually what you want for a code change - it zooms to what moved instead of a full page. Get diffResultId from get_build (changedStories[].diffResultId) or get_diff. (2) a build selector (commitSha|prNumber|buildId) + storyId for ANY story's current image - the candidate if it changed this build, else its baseline. This second form is the only way to see an UNCHANGED/passed story's pixels (list them via list_build_stories status=unchanged), so you can confirm 'identical to baseline'. Errors if the image doesn't exist (a genuinely new story has no baseline, so no before_after either).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
whichNoFor the diffResultId form: baseline|candidate|diff (one triptych image, default candidate), or before_after (baseline+candidate side by side, cropped to the change - one crop per changed region, stacked, when the change spans several places). Ignored for the storyId form.
buildIdNoResolve this exact build id.
storyIdNoWith a build selector: fetch THIS story's current image (works for unchanged stories).
prNumberNoResolve the latest build for this PR number.
commitShaNoResolve the build for this git commit SHA.
diffResultIdNoA CHANGED story's diff result id (from get_build/get_diff); pair with `which`.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A5/5.0
Behavior5/5

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

Even though annotations already declare readOnlyHint=true, the description adds substantial behavioral context: output is inline base64, before_after crops to changed regions and stacks multiple crops, and the tool errors when an image genuinely doesn't exist. This goes well beyond the annotations and fully discloses the tool's runtime behavior.

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

Conciseness5/5

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

The description is long but every sentence earns its place; the tool genuinely has two distinct invocation modes and nuanced image-format behavior. It is front-loaded with the core purpose, then logically organized into the two addressing forms, with caveats placed in context.

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 tool with 6 optional parameters, two call forms, no output schema, and no nested objects, the description fully covers the invocation methods, image variants, error behavior, and how to get the required IDs. Nothing needed to call the tool correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the schema already documents each parameter. The description goes further by explaining the two valid parameter combinations, the meaning of each `which` value (including before_after's side-by-side crop behavior), and how to obtain diffResultId from get_build/get_diff. This transforms the flat parameter list into actionable usage knowledge.

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 description states a specific verb and resource: fetch a story's image as an inline base64 image for vision-model consumption. It clearly distinguishes itself from get_diff by noting that get_diff returns URLs while this tool returns pixels, so an agent can tell them apart.

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?

The description explicitly says when to use this tool (vision-model needs pixels), when NOT to use it (piped through raw curl, use get_diff's URLs), and gives two concrete addressing forms with step-by-step guidance. It also identifies the only way to view unchanged/passed story pixels, leaving no ambiguity about tool selection.

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

All UI Verify toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation4/5

Most tools target distinct resources and actions, and the descriptions carefully separate build triage from PR changesets. However, get_diff and render_diff_image both provide diff imagery (URLs vs inline), and accept_build overlaps with review_diff's accept mode, so one or two selections could be mis-picked without reading closely.

Naming Consistency5/5

All nine tools use a consistent snake_case verb_noun pattern: list_* for paginated listings, get_* for detail/triage, render_* for image output, and review_diff/accept_build for review actions. The naming convention is predictable and easy to reason about.

Tool Count5/5

Nine tools is well within the ideal scope for a visual-regression review server. Each tool maps to a distinct workflow step—finding builds, triaging results, paging stories, fetching images, and recording reviews—without redundant or bloated additions.

Completeness5/5

The tool surface covers the full UI-verification loop: discover builds, inspect gate verdicts, page through changed/failed/unchanged stories, fetch diff details and inline images, review individually or bulk-accept, and inspect PR-level visual changesets. No essential operation for the stated domain is missing.

Resources