Skip to main content
Glama

Screenshot and analyze live websites

inspo_capture

Capture hero and full-page screenshots of live websites, then extract fonts, colors, radii, type scale, and tech stack for design reference research.

Instructions

Screenshot specific live websites (hero + full page) and extract their design DNA: fonts, color palette, radii, type scale and tech (three.js, GSAP, Lenis, Webflow, Framer, Spline...). Use it for great references you already know for this niche (e.g. stripe.com, linear.app, a competitor) and for Awwwards winners found by inspo_search.

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": {
      "urls": "<urls>"
    },
    "name": "inspo_capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
whyNoWhy these were picked; shown on the cards.
urlsYes
mobileNoCapture at iPhone size instead of desktop.
sectionNoTag the captures as references for this section.
sessionNoSession id. Defaults to the most recent session in this project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the capture modes (hero + full page, optional mobile/iPhone size) and the extracted artifacts, but says nothing about latency, cost, failure handling for unreachable URLs, or whether inspo_login is a prerequisite — meaningful gaps for a tool that drives a headless browser across up to 12 sites.

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?

Two sentences, no filler, with the capture scope and extracted outputs front-loaded ahead of the usage scenario. The parenthetical tech list is long but genuinely informative about detection coverage. Slightly dense, though nothing is redundant.

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?

For a five-parameter tool with no annotations and no output schema, the description partially compensates by enumerating what the extracted design DNA contains, which effectively sketches the return payload. It leaves out operational realities: timing, credits, auth, and per-URL failure behavior — the things an agent most needs before committing a batch of twelve URLs.

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 80%, so urls, why, mobile, section, and session are already documented in the schema. The description adds domain framing (these are live production sites worth referencing) but no format rules, ordering behavior, or guidance on how the 12-URL cap should be spent. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Names a specific verb and resource — screenshot live websites (hero + full page) and extract design DNA: fonts, color palette, radii, type scale, tech stack. The term 'specific live websites' plus the enumerated extraction outputs separates it cleanly from inspo_search, which is described as finding references rather than capturing them.

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

Usage Guidelines4/5

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

Gives concrete when-to-use guidance: references you already know for this niche (stripe.com, linear.app, a competitor) or Awwwards winners surfaced by inspo_search. That establishes an upstream dependency on inspo_search and a clear triggering context. It stops short of stating exclusions or what to do instead when a URL is already captured.

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