Skip to main content
Glama
DICloak Local API MCP Server

DICloak Local API MCP Server

Official

take_screenshot

Capture full-page or element-specific screenshots in a DICloak browser environment by specifying an environment ID and optional CSS selector.

Instructions

Take a screenshot of the current page or a specific element in the browser environment (if you want to see the page, recommend to use chrome_get_web_content first)

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": {
      "envId": "<envId>"
    },
    "name": "take_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoName for the screenshot, if saving as PNG
envIdYesEnvironment ID for the browser environment to operate.
widthNoWidth in pixels, skip it if not needed
heightNoHeight in pixels, skip it if not needed
savePngNoSave screenshot as PNG file (default: true), if you want to see the page, recommend set this to be false, and set storeBase64 to be true
fullPageNoStore screenshot of the entire page (default: true)
selectorNoCSS selector for element to screenshot
storeBase64NoReturn screenshot in base64 format (default: false) if you want to see the page, recommend set this to be true

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden and mostly doesn't: it never says the tool writes a PNG file to disk (a side effect implied by savePng default true), where that file lands, or what the call returns when storeBase64 is false. The only added context is the routing hint to chrome_get_web_content; the rest of the behavioral detail lives in the schema, not the description.

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?

One front-loaded sentence plus a parenthetical tip, with no filler. The trailing recommendation is slightly awkwardly nested but costs little.

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 an 8-parameter tool with no output schema, the description is thin: it never describes the return shape (base64 payload vs. saved file reference) or the fact that capturing produces a file artifact. It is saved somewhat by an unusually thorough input schema, but an agent still lacks guidance on how to read the result.

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 the schema already explains name, width, height, savePng, fullPage, selector and storeBase64 in detail. The description adds no parameter-level meaning beyond echoing the 'see the page' guidance, so baseline 3 applies.

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 states a specific verb and resource ('take a screenshot of the current page or a specific element') and scopes it to 'the browser environment', which is enough for an agent to know what it does. It further distinguishes itself from the sibling chrome_get_web_content by noting that tool is preferable for simply reading page content, though that differentiation is brief.

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?

It explicitly names an alternative (chrome_get_web_content) and the condition that selects it ('if you want to see the page, recommend to use chrome_get_web_content first'), giving the agent a routing rule. It does not discuss when to prefer full-page vs. element capture, but the schema's fullPage/selector descriptions largely cover that.

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