Skip to main content
Glama
vuluu2k

sbuilder-mcp

by vuluu2k
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

sb_look

Idempotent

Renders and returns screenshots of web pages at desktop, tablet, and mobile widths, with optional node-specific framing and layout defect detection for overflow, overlap, and unreadable text.

Instructions

Save, render through the platform's own renderer, and return screenshots at desktop, tablet and mobile widths, measured boxes for the bands and their children, and any layout defect measured on the render (overflow, overlap, unreadable text). node_id frames one element. Judge your work from these, not from memory.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoShoot this address instead of the draft preview — use the PUBLISHED storefront URL to see real store data
formatNojpeg (default) is smaller and faster; png for pixel-exact colour
widthsNo
node_idNoFrame just this node instead of the whole page — how a designer looks at one card
box_depthNoBoxes down to this depth in the tree (default 2: bands and their children)
with_boxesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.0
    • addedInput schema / properties / url
      Added value: +{
+  "description": "Shoot this address instead of the draft preview — use the PUBLISHED storefront URL to see real store data",
+  "type": "string"
+}
  2. First observedv0.1.4

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare idempotentHint=true and destructiveHint=false, so the description does not need to repeat those. It adds valuable context about the platform's own renderer, the outputs (screenshots, boxes, defects), and the node_id framing behavior, which goes beyond the structured annotations. No contradiction with annotations.

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 two sentences: the first front-loads the core purpose and outputs, the second gives usage guidance. Every word serves a purpose, with no filler or repetition.

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

Completeness3/5

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

The description covers the main outputs (screenshots, boxes, defects) and gives purpose, but it does not specify the response structure or how to interpret the defect data. It also omits details on the widths array and with_boxes parameter, leaving some ambiguity for a tool with 6 parameters and no output schema.

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

Parameters3/5

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

Schema description coverage is 67%, so the baseline is 3. The description adds meaning for url (via published storefront mention), format (jpeg/png), node_id (frames one element), and box_depth (bands and children), but it does not clarify the widths array format or with_boxes behavior, which lack schema descriptions. It partially compensates for the coverage gap but not fully.

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

Purpose4/5

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

The description clearly states the tool saves, renders, and returns screenshots at multiple widths, measured boxes, and layout defects, giving a specific verb and resource. It also mentions node_id to frame one element, but does not explicitly contrast with sibling tools like sb_outline or sb_node_read, though the features are distinct enough.

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

Usage Guidelines3/5

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

The description implies usage for visual evaluation with 'Judge your work from these, not from memory,' giving context on when to use it. However, it does not explicitly state when not to use it or name alternatives among the many sibling tools, leaving routing to inference.

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

Deploy Server

Other Tools