Skip to main content
Glama
mcp-cui-chrome

mcp-cui-chrome

by cuipy

拟人点击

browser_click

Clicks a page element by its snapshot reference in Chrome, previewing the target before and reporting success or navigation after; blocked targets fail instead of clicking through.

Instructions

通用:按快照编号点击。开始前显示要点的元素,结束后显示是否成功、页面有没有跳转。落点被别的内容挡住时会失败,不点穿过去。

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": {
      "ref": "<ref>"
    },
    "name": "browser_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYes快照里的元素编号,例如 e3
buttonNo鼠标按键,默认左键

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.4

TDQS

A3.7/5.0
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 well: it discloses pre-click element preview, post-click success/navigation feedback, and a specific failure mode — occlusion causes failure with no click-through, implying real coordinate-level clicking rather than forced/JS dispatch. It does not cover timeouts, auto-scroll into view, or what right/middle button do beyond the schema default.

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?

Three short, front-loaded clauses: purpose first, then pre/post feedback, then the failure constraint. Every sentence earns its place; the only minor weakness is the slightly repetitive '显示…显示…' phrasing, which could be tightened.

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?

With no annotations and no output schema, the description must cover both behavior and return signals, and it does — it states the agent will see the target element before and success/navigation status after. For a two-parameter click tool this is nearly complete, missing only edge details like timing or what happens on non-left buttons.

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% — the ref parameter already explains the snapshot element id with an example (e3) and the button enum already documents the default left button. The description only restates the ref-based targeting, adding no meaning about how button choice affects behavior, so the 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 gives a concrete verb and resource ('按快照编号点击' — click by snapshot ref), and the prefix '通用' signals this is the default/general click versus more specialized siblings like browser_drag, browser_hover, browser_press, and browser_type. It stops short of naming any sibling explicitly, so the differentiation is implied rather than stated.

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?

The word '通用' implies this is the go-to click tool, and the failure condition (an occluded landing point fails rather than clicking through) tells the agent when a click will not work. However, there is no explicit when-to-use/when-not guidance and no named alternative (e.g. for right-click context menus or keyboard activation), leaving routing to inference.

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