Skip to main content
Glama

Capturar e entender o design de uma página

designeer_capture

Capture any URL in headless Chrome to extract design tokens, page structure, and component CSS recipes for copying into your project. Choose full-page or 390px mobile views.

Instructions

Abre uma URL no Chrome/Edge instalado (headless), tira print da página inteira (em fatias, só na memória) e lê como ela é feita: DESIGN (cores de fundo/texto/borda em hex, fontes+peso, escala de tamanhos, raios, sombras, CSS vars) e ESTRUTURA (seções em ordem com altura/fundo/título/layout, largura do container, grids e flex com gap, escala de espaçamento, e a receita dos componentes — botões, cards, inputs, badges — com seletor de cada um). Use o 'selector' de um componente ou seção em designeer_component pra copiar o código dele. Aceita path de listing do Designeer (resolve pro site oficial). Páginas atrás de login não funcionam.

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": {
      "url": "<url>"
    },
    "name": "designeer_capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
dirNoPasta destino quando save=true
urlYesURL a capturar, ou path de listing do Designeer (ex: 'tools/revone')
saveNoGuardar os prints em ~/designeer-media (padrão: só memória)
mobileNoCaptura em 390px (mobile) em vez de 1440px
max_heightNoAltura máxima do print em px

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: headless Chrome/Edge, slices kept in memory only by default, opt-in persistence to disk, and the login-wall limitation. It does not mention timeouts, JS/SPA rendering behavior, or cost/latency for large captures, which are the main remaining unknowns for a network-bound tool.

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?

Front-loaded with the action, and the DESIGN/STRUCTURE enumeration is dense but each item is informative rather than filler. The first sentence is very long and packs the whole payload list, but nothing is wasted and the two follow-up sentences are short and purposeful.

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, no-annotation tool with no output schema, the description gives an unusually good picture of what comes back (color/font/scale tokens plus structural layout and component recipes). Exact response shape and pagination/truncation behavior for very tall pages are unstated, which is a minor residual gap rather than a blocking one.

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 100%, so every parameter (url, save, dir, mobile, max_height) is already documented in the schema. The description only reinforces two of them (listing paths for url, in-memory default vs. saving) and says nothing about mobile viewport or max_height. Baseline 3 is appropriate since 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?

States a concrete verb and resource chain — opens a URL headlessly, screenshots the full page in memory, and extracts DESIGN (hex colors, fonts/weights, scales, radii, shadows, CSS vars) and STRUCTURE (ordered sections, container width, grid/flex gaps, component recipes with selectors). This is specific enough that an agent can distinguish it from browse/search/component siblings without opening any schema.

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?

Provides a clear use context (analyze how a page is built) plus a cross-tool handoff: use the 'selector' surfaced here in designeer_component to copy a component's code. It also states the exclusion 'Páginas atrás de login não funcionam' and that Designeer listing paths are accepted. Missing an explicit statement of when a sibling like designeer_browse would be preferred instead.

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