Playwright MCP

browser_type

Destructive

Type text into web page elements for browser automation, supporting character-by-character input and form submission.

Instructions

Type text into editable element

Input Schema

TableJSON Schema

Name	Required	Description
`element`	Yes	Human-readable element description used to obtain permission to interact with the element
`ref`	Yes	Exact target element reference from the page snapshot
`text`	Yes	Text to type into the element
`submit`	No	Whether to submit entered text (press Enter after)
`slowly`	No	Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.

Implementation Reference

src/tools/keyboard.ts:64-85 (handler)

The core handler function for the 'browser_type' tool. It locates the target element using the provided ref, then either fills the text instantly or types it sequentially if 'slowly' is true, and optionally presses Enter if 'submit' is true.

handle: async (tab, params, response) => {
  const locator = await tab.refLocator(params);

  await tab.waitForCompletion(async () => {
    if (params.slowly) {
      response.setIncludeSnapshot();
      response.addCode(`// Press "${params.text}" sequentially into "${params.element}"`);
      response.addCode(`await page.${await generateLocator(locator)}.pressSequentially(${javascript.quote(params.text)});`);
      await locator.pressSequentially(params.text);
    } else {
      response.addCode(`// Fill "${params.text}" into "${params.element}"`);
      response.addCode(`await page.${await generateLocator(locator)}.fill(${javascript.quote(params.text)});`);
      await locator.fill(params.text);
    }

    if (params.submit) {
      response.setIncludeSnapshot();
      response.addCode(`await page.${await generateLocator(locator)}.press('Enter');`);
      await locator.press('Enter');
    }
  });
},

src/tools/keyboard.ts:48-62 (schema)

Defines the input schema for the 'browser_type' tool, extending elementSchema with text, submit, and slowly options.

const typeSchema = elementSchema.extend({
  text: z.string().describe('Text to type into the element'),
  submit: z.boolean().optional().describe('Whether to submit entered text (press Enter after)'),
  slowly: z.boolean().optional().describe('Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.'),
});

const type = defineTabTool({
  capability: 'core',
  schema: {
    name: 'browser_type',
    title: 'Type text',
    description: 'Type text into editable element',
    inputSchema: typeSchema,
    type: 'destructive',
  },

src/tools/snapshot.ts:39-42 (schema)

Shared base schema for element targeting (element description and snapshot ref), used as foundation for browser_type input schema.

export const elementSchema = z.object({
  element: z.string().describe('Human-readable element description used to obtain permission to interact with the element'),
  ref: z.string().describe('Exact target element reference from the page snapshot'),
});

src/tools.ts:36-52 (registration)

Global registration of all MCP tools by aggregating exports from individual tool modules, including 'browser_type' via ...keyboard.

export const allTools: Tool<any>[] = [
  ...common,
  ...console,
  ...dialogs,
  ...evaluate,
  ...files,
  ...install,
  ...keyboard,
  ...navigate,
  ...network,
  ...mouse,
  ...pdf,
  ...screenshot,
  ...snapshot,
  ...tabs,
  ...wait,
];

src/tools/keyboard.ts:88-91 (registration)
Local registration: exports the keyboard tools array including the 'browser_type' tool (named 'type' internally).
```
export default [
  pressKey,
  type,
];
```

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 readOnlyHint=false, openWorldHint=true, and destructiveHint=true, covering safety and scope. The description adds context by specifying it types into 'editable element,' which clarifies the target beyond annotations. It doesn't contradict annotations, but lacks details on side effects (e.g., triggering events) or error handling, though annotations provide a good baseline.

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 ('Type text into editable element') with zero waste. It efficiently conveys the core purpose without unnecessary elaboration, making it highly concise and well-structured for quick understanding.

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 complexity (interactive browser action with 5 parameters), annotations provide good behavioral context (destructive, open-world), and schema coverage is 100%. However, no output schema exists, and the description lacks details on return values or error cases. It's adequate but has gaps in completeness for a mutation tool.

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%, with clear parameter descriptions in the schema (e.g., 'element' for permission, 'ref' for target, 'slowly' for character-by-character typing). The description doesn't add meaning beyond the schema, but the schema is comprehensive, so a baseline score of 3 is appropriate as it doesn't compensate or detract.

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 'Type text into editable element' clearly states the action (type) and target (editable element), distinguishing it from siblings like browser_click or browser_press_key. However, it doesn't explicitly differentiate from browser_select_option or browser_file_upload, which also involve input actions, making it clear but not fully sibling-differentiated.

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., needing a page snapshot from browser_snapshot), exclusions (e.g., non-editable elements), or comparisons to siblings like browser_press_key for key presses or browser_select_option for dropdowns.

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