Playwright MCP

browser_resize

Destructive

Adjust browser window dimensions for testing responsive web designs or capturing specific viewport states during automation.

Instructions

Resize the browser window

Input Schema

TableJSON Schema

Name	Required	Description	Default
`width`	Yes	Width of the browser window
`height`	Yes	Height of the browser window

Implementation Reference

src/tools/common.ts:54-72 (handler)

The handler function for the 'browser_resize' tool. It resizes the viewport size of the current browser tab using the provided width and height parameters, generates a code snippet representing the action, defines an action to execute the resize, and returns the necessary metadata for execution.

handle: async (context, params) => {
  const tab = context.currentTabOrDie();

  const code = [
    `// Resize browser window to ${params.width}x${params.height}`,
    `await page.setViewportSize({ width: ${params.width}, height: ${params.height} });`
  ];

  const action = async () => {
    await tab.page.setViewportSize({ width: params.width, height: params.height });
  };

  return {
    code,
    action,
    captureSnapshot,
    waitForNetwork: true
  };
},

src/tools/common.ts:43-52 (schema)

The schema definition for the 'browser_resize' tool, including name, title, description, input schema validating width and height as numbers, and type as readOnly.

schema: {
  name: 'browser_resize',
  title: 'Resize browser window',
  description: 'Resize the browser window',
  inputSchema: z.object({
    width: z.number().describe('Width of the browser window'),
    height: z.number().describe('Height of the browser window'),
  }),
  type: 'readOnly',
},

src/tools.ts:35-50 (registration)

Registration of the browser_resize tool as part of the snapshotTools array, imported via common(true) which includes the resize tool.

export const snapshotTools: Tool<any>[] = [
  ...common(true),
  ...console,
  ...dialogs(true),
  ...files(true),
  ...install,
  ...keyboard(true),
  ...navigate(true),
  ...network,
  ...pdf,
  ...screenshot,
  ...snapshot,
  ...tabs(true),
  ...testing,
  ...wait(true),
];

src/tools.ts:52-66 (registration)

Registration of the browser_resize tool as part of the visionTools array, imported via common(false) which includes the resize tool.

export const visionTools: Tool<any>[] = [
  ...common(false),
  ...console,
  ...dialogs(false),
  ...files(false),
  ...install,
  ...keyboard(false),
  ...navigate(false),
  ...network,
  ...pdf,
  ...tabs(false),
  ...testing,
  ...vision,
  ...wait(false),
];

Schema Changelog

Changes observed during successful MCP inspections.

First observedAug 15, 2025

TDQS

A3.5/5.0

Behavior4/5

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

Annotations indicate destructiveHint=true and readOnlyHint=false, which the description aligns with by implying a mutation (resizing). The description adds context beyond annotations by specifying it affects the 'browser window' (not just a tab or element), but doesn't detail side effects (e.g., might trigger page reloads, affect viewport-dependent content). No contradiction with annotations, and it provides some useful behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence ('Resize the browser window') that directly conveys the core function without any wasted words. It's appropriately sized for a simple tool and earns its place by clearly stating the action and target.

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?

Given the tool's moderate complexity (a destructive operation with two parameters), the description is minimally adequate. Annotations cover safety (destructive) and mutability, and the schema fully documents parameters. However, with no output schema, the description doesn't explain return values (e.g., success confirmation, error handling), and it lacks context about integration with sibling tools. It meets basic needs but has clear gaps.

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?

The input schema has 100% description coverage, with clear documentation for width and height parameters. The description doesn't add any meaning beyond the schema (e.g., units, valid ranges, or default behaviors). According to the rules, with high schema coverage, the baseline is 3, which is appropriate here as the schema carries the full burden of parameter documentation.

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 'Resize the browser window' clearly states the action (resize) and resource (browser window), making the purpose immediately understandable. It distinguishes from siblings like browser_close or browser_navigate by specifying the resize operation. However, it doesn't explicitly differentiate from all siblings (e.g., browser_snapshot might also involve window dimensions), so it falls short of a perfect 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., requires an active browser session), exclusions (e.g., not for mobile browsers), or context (e.g., use before taking screenshots for consistent sizing). With siblings like browser_take_screenshot that might benefit from resizing, this lack of guidance is a significant gap.

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