Skip to main content
Glama

screen_open

Idempotent

Open a web page in the browser Arsaze records, on the user's computer (its own profile, not the user's sign-ins). Returns the page: elements to act on with refs, headings, scroll, and a screenshot. width x height is the page in CSS pixels; the video is that times scale (default 1280x720 at 1.5 = 1920x1080). Nothing is recorded until screen_record_start.

response_detail (summary|ids|compact|full), fields (dotted paths), cursor (next page) — see the server instructions.

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": "screen_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
scaleNo
whereNo
widthNo
cursorNo
fieldsNo
heightNo
response_detailNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / where
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Where"
      +}
  2. Added

TDQS

A3.6/5.0
Behavior4/5

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

The annotations declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=false, but they say nothing about the isolation model or the side effects. Beyond them, the description adds the crucial fact that the browser uses its own profile and not the user's sign-ins, which matters for authentication and privacy. It also states that nothing is recorded until screen_record_start, and it explains how CSS pixels relate to video resolution. It stops short of saying whether the page state persists across calls or how long the session stays open.

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?

The core behavior is front-loaded in the first two sentences, and the width/height/scale relation is compressed into one clause. The trailing fragment listing response_detail, fields, and cursor is telegraphic and defers to the server instructions, which is efficient but reads as an afterthought.

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?

This is a fairly complex tool with eight parameters, no output schema, and no schema descriptions, so the description carries a heavy load. It does describe the returned page well enough to stand in for the missing output schema, but it leaves 'where' undefined and gives only a pointer for the pagination and field-selection parameters.

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 0%, so the description has to carry all eight parameters, and it does so partially. It gives value ranges for response_detail (summary|ids|compact|full), describes the pair width x height in CSS pixels, explains scale by relating it to the video, and gives cursor as 'next page'. But it never explains 'where', and it touches 'url' only indirectly, leaving one of the eight parameters undocumented.

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: 'Open a web page in the browser' on the user's computer. That phrasing implicitly distinguishes this tool from the sibling screen_open_app, which opens apps rather than pages, although it never names that sibling. It also tells the agent what comes back (elements with refs, headings, scroll, screenshot), so the agent can tell what kind of tool this is without opening the schema.

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?

It implies when to use the tool ('open a web page') and passes along one boundary rule, that nothing is recorded until screen_record_start. But it never names an alternative or states when not to use it. The agent has to infer for itself when to choose screen_open over screen_open_app or a browser-less tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.