Skip to main content
Glama
mcp-cui-chrome

mcp-cui-chrome

by cuipy

截图

browser_screenshot

Capture the current browser viewport as an image for AI assistants driving a local Chrome session. Returns the screenshot with a clear success or failure result after noting the action on the page.

Instructions

通用:截取当前视口。开始前在页面上说明,结束后返回图片并标明成功或失败。

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": "browser_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.4

TDQS

A3.6/5.0
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 disclosure burden. It does add genuinely useful behavior beyond the name: it says to explain the action on the page beforehand and that the result is an image with a success/failure indication. However, it omits whether the capture needs any permission, what region or size the image covers, and whether the tool blocks or costs anything, which are the kinds of traits an unannotated tool should surface.

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 short sentences, front-loaded with the core purpose and followed by the operational instruction. Nothing is padded or redundant, though the pre-announcement instruction sits a little awkwardly next to the purpose statement.

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 zero-parameter, unannotated tool with no output schema, the definition covers the essential loop: what is captured, the expected pre-action, and the return type (an image plus success/failure). It stops short of describing what a failure case looks like or any constraints on when the capture is valid, but it is close to complete for this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is no parameter semantics to add and the baseline is 4. The description correctly stays silent on inputs rather than inventing options.

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 concrete verb+resource combination ('capture the current viewport') and prefixes it with '通用' (general-purpose), which hints it is the default capture path rather than a specialized one. It does not explicitly contrast with the sibling browser_snapshot, so an agent must infer the distinction between a viewport image and a DOM snapshot.

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?

'通用' (general) implies broad applicability with no exclusions, and the instruction to announce the action on the page before starting gives some procedural context. There is no explicit when-to-use versus when-not-to-use guidance and no mention of the closest alternative, browser_snapshot, leaving selection partly to inference.

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