Skip to main content
Glama
Sign In

Fudge for Shopify

by ai.fudge
OverviewDiscussionsAdmin

Capture page screenshots

capture_page
Read-onlyIdempotent

Screenshot one store page in a real browser on desktop and/or mobile and return the images. Pass draft to see a Fudge draft. fullPage captures top to bottom. Takes 15–60 seconds; up to 50 captures per store per day.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "capture_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoA store URL or path, e.g. / or /products/blue-runner. Defaults to the home page, or with `draft` to the page the draft is about.
draftNoA draft’s fudge://project/… ref: capture the page as that draft shows it. Staged product and page content changes appear only on Fudge’s review page, not here.
storeNoThe connected store to use. Omit when only one is connected.
deviceNoboth
fullPageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world, so the description's added value is operational: 15–60 second runtime, a 50-captures-per-store-per-day quota, and the fact that captures run in a real browser. Those are exactly the traits an agent needs to plan around. It falls short of 5 by not saying what happens on failure (bad URL, page not found) or what the returned images look like.

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?

Three short sentences, front-loaded with the core action and output, then the two most relevant options, then the cost signal. No filler or restated title.

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

Completeness4/5

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

For a 5-parameter, all-optional capture tool with no output schema, the description covers purpose, key options, timing, and quotas. The draft caveat (staged changes only appear on Fudge's review page) is a useful expectation-setting detail. Gaps are minor: return shape of the image set and failure behavior are unstated.

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 coverage is 60%, so the schema already documents `page`, `draft`, and `store`. The description restates `draft` ('see a Fudge draft') and `fullPage` ('captures top to bottom') — the latter without even naming the parameter — and gestures at `device` via 'desktop and/or mobile'. It adds little semantic detail beyond the schema, and `store` is untouched, so it does not compensate for the coverage gap.

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?

States a specific verb and resource — screenshot one store page — plus the mechanism (a real browser), the scope (desktop and/or mobile), and the output (the images). The emphasis on returning images distinguishes it from checking/auditing siblings like check_page without needing to name them.

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?

Usage is only implied: an agent infers you call this when you want a visual capture of a page. The sentences about `draft` and `fullPage` are parameter guidance, not when-to-use routing. There is no explicit statement of when to prefer this over check_page or other page-inspection siblings, though the latency and daily cap hint at cost-driven selection.

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

All Fudge for Shopify toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources