Skip to main content
Glama
Hermoso

Hermoso

Official

Fetch App Store screens

fetch_app_screens
Idempotent

Pull a brand's real App Store or Google Play screenshots into the workspace, or grab the interface images from its own website, so app-ui-tour ads have screens to use.

Instructions

Pull an APP brand's REAL store screenshots (Google Play or App Store) into the workspace brand, so a screen-hungry native format can use them. Use when the brand has 0–1 app screens on file and you want make_template_ad(template:'app-ui-tour'), or the user asks to 'pull my app's screenshots'. A store link or package id goes in storeUrl and is read exactly; else pass appName (defaults to the saved brand's name). A web app with no store listing gets the screenshots of the product its OWN website shows (pictures the site labels as its interface). Call it before telling the user you have no screenshots of their app. FREE — a keyless store lookup or one read of the brand's homepage. It needs a CONFIDENT match: an ambiguous or unknown app returns 0 screens and saves nothing, which you should relay plainly rather than retrying with guesses. On success the screens are saved to the brand (durable URLs) and are immediately usable.

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": "fetch_app_screens"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNameNothe app's name to look up on the App Store — defaults to the saved brand's name
brandIdNoa profile id/name from list_brands to save the screens onto; omit to use the active profile
storeUrlNoa Google Play / App Store link or package id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.454
    • addedInput schema / properties / storeUrl
      Added value: +{
      +  "description": "a Google Play / App Store link or package id",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv0.1.374
    • changedInput schema / properties / brandId / description
      Previous value: -"a brand id/name from list_brands to save the screens onto; omit to use the active brand"New value: +"a profile id/name from list_brands to save the screens onto; omit to use the active profile"
  3. Addedv0.1.161

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with a write-to-brand operation. Beyond that it discloses cost ('FREE — a keyless store lookup or one read of the homepage'), the failure mode (ambiguous/unknown app returns 0 screens and saves nothing), and the success side effect (screens saved to the brand as durable URLs, immediately usable). Only the exact return payload shape is left implicit.

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?

It is front-loaded with the purpose and trigger, then stacks preconditions, fallbacks, cost, and failure handling in a logical order with zero filler sentences. It is on the dense/long side for a three-parameter tool and could compress the web-app fallback clause, but nothing is redundant.

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 no output schema and an external-dependency (open-world) lookup, the description covers inputs, the no-store fallback, the zero-result failure behavior with guidance not to retry, cost, and where results land. An agent has everything needed to call it once correctly and interpret the outcome.

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 100% and the schema already documents appName defaults to the saved brand's name and that storeUrl takes a link or package id, so the description largely restates it ('storeUrl ... is read exactly; else pass appName'). It does add genuinely new meaning for storeUrl-less web apps — falling back to pictures the product's own website labels as its interface. With the schema doing the heavy lifting, this sits at the baseline plus one useful addition.

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 names a specific verb and resource — pulling real Google Play / App Store screenshots into the workspace brand — and distinguishes itself from siblings like fetch_asset or list_product_photos by scoping it to app-store screens used by screen-hungry native formats. An agent can tell exactly what it produces 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?

It gives an explicit trigger condition ('brand has 0–1 app screens on file'), a concrete downstream use (make_template_ad with template:'app-ui-tour'), a natural-language user phrasing, and a pre-emption rule ('Call it before telling the user you have no screenshots'). It also steers the agent away from retrying with guessed names, which is an explicit when-not.

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