Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Playwright MCP Navigate to news.ycombinator.com and summarize the top story"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.
This package provides MCP interface into Playwright. If you are using a coding agent, you might benefit from using the CLI+SKILLS instead.
CLI: Modern coding agents increasingly favor CLI–based workflows exposed as SKILLs over MCP because CLI invocations are more token-efficient: they avoid loading large tool schemas and verbose accessibility trees into the model context, allowing agents to act through concise, purpose-built commands. This makes CLI + SKILLs better suited for high-throughput coding agents that must balance browser automation with large codebases, tests, and reasoning within limited context windows.Learn more about Playwright CLI with SKILLS.
MCP: MCP remains relevant for specialized agentic loops that benefit from persistent state, rich introspection, and iterative reasoning over page structure, such as exploratory automation, self-healing tests, or long-running autonomous workflows where maintaining continuous browser context outweighs token cost concerns.
Fast and lightweight. Uses Playwright's accessibility tree, not pixel-based input.
LLM-friendly. No vision models needed, operates purely on structured data.
Deterministic tool application. Avoids ambiguity common with screenshot-based approaches.
Node.js 18 or newer
VS Code, Cursor, Windsurf, Claude Desktop, Goose, Grok, Junie or any other MCP client
First, install the Playwright MCP server with your client.
Standard config works in most of the tools:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}
Add via the Amp VS Code extension settings screen or by updating your settings.json file:
"amp.mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}Amp CLI Setup:
Add via the amp mcp add command below
amp mcp add playwright -- npx @playwright/mcp@latestAdd via the Antigravity settings or by updating your configuration file:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}Use the Claude Code CLI to add the Playwright MCP server:
claude mcp add playwright npx @playwright/mcp@latestFollow the MCP install guide, use the standard config above.
Follow the instruction in the section Configuring MCP Servers
Example: Local Setup
Add the following to your cline_mcp_settings.json file:
{
"mcpServers": {
"playwright": {
"type": "stdio",
"command": "npx",
"timeout": 30,
"args": [
"-y",
"@playwright/mcp@latest"
],
"disabled": false
}
}
}Use the Codex CLI to add the Playwright MCP server:
codex mcp add playwright npx "@playwright/mcp@latest"Alternatively, create or edit the configuration file ~/.codex/config.toml and add:
[mcp_servers.playwright]
command = "npx"
args = ["@playwright/mcp@latest"]For more information, see the Codex MCP documentation.
Use the Copilot CLI to interactively add the Playwright MCP server:
/mcp addAlternatively, create or edit the configuration file ~/.copilot/mcp-config.json and add:
{
"mcpServers": {
"playwright": {
"type": "local",
"command": "npx",
"tools": [
"*"
],
"args": [
"@playwright/mcp@latest"
]
}
}
}For more information, see the Copilot CLI documentation.
Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command npx @playwright/mcp@latest. You can also verify config or add command like arguments via clicking Edit.
Use the Factory CLI to add the Playwright MCP server:
droid mcp add playwright "npx @playwright/mcp@latest"Alternatively, type /mcp within Factory droid to open an interactive UI for managing MCP servers.
For more information, see the Factory MCP documentation.
Follow the MCP install guide, use the standard config above.
Go to Advanced settings -> Extensions -> Add custom extension. Name to your liking, use type STDIO, and set the command to npx @playwright/mcp. Click "Add Extension".
Use the Grok CLI to add the Playwright MCP server:
grok mcp add playwright -- npx @playwright/mcp@latestAlternatively, create or edit the configuration file ~/.grok/config.toml and add:
[mcp_servers.playwright]
command = "npx"
args = ["@playwright/mcp@latest"]For more information, see the Grok MCP documentation.
To add the Playwright MCP server in Junie CLI:
Type /mcp
Press Ctrl+A to add a new MCP server
Select Playwright from the list
Alternatively, add to .junie/mcp/mcp.json:
{
"mcpServers": {
"Playwright": {
"command": "npx",
"args": [
"-y",
"@playwright/mcp@latest"
]
}
}
}For more information, see the Junie MCP configuration documentation.
Follow the MCP Servers documentation. For example in .kiro/settings/mcp.json:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}
Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the standard config above.
Follow the MCP Servers documentation. For example in ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"playwright": {
"type": "local",
"command": [
"npx",
"@playwright/mcp@latest"
],
"enabled": true
}
}
}
Open Qodo Gen chat panel in VSCode or IntelliJ → Connect more tools → + Add new MCP → Paste the standard config above.
Click Save.
Follow the MCP install guide, use the standard config above. You can also install the Playwright MCP server using the VS Code CLI:
# For VS Code
code --add-mcp '{"name":"playwright","command":"npx","args":["@playwright/mcp@latest"]}'After installation, the Playwright MCP server will be available for use with your GitHub Copilot agent in VS Code.
Go to Settings -> AI -> Manage MCP Servers -> + Add to add an MCP Server. Use the standard config above.
Alternatively, use the slash command /add-mcp in the Warp prompt and paste the standard config from above:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}Follow Windsurf MCP documentation. Use the standard config above.
Playwright MCP server supports following arguments. They can be provided in the JSON configuration above, as a part of the "args" list:
Option | Description |
--allowed-hosts <hosts...> | comma-separated list of hosts this server is allowed to serve from. Defaults to the host the server is bound to. Pass '*' to disable the host check.env |
--allowed-origins | semicolon-separated list of TRUSTED origins to allow the browser to request. Default is to allow all. Important: does not serve as a security boundary and does not affect redirects.env |
--allow-unrestricted-file-access | allow access to files outside of the workspace roots. Also allows unrestricted access to file:// URLs. By default access to file system is restricted to workspace root directories (or cwd if no roots are configured) only, and navigation to file:// URLs is blocked.env |
--blocked-origins | semicolon-separated list of origins to block the browser from requesting. Blocklist is evaluated before allowlist. If used without the allowlist, requests not matching the blocklist are still allowed. Important: does not serve as a security boundary and does not affect redirects.env |
--block-service-workers | block service workersenv |
--browser | browser or chrome channel to use, possible values: chrome, firefox, webkit, msedge.env |
--caps | comma-separated list of additional capabilities to enable, possible values: vision, pdf, devtools.env |
--cdp-endpoint | CDP endpoint to connect to.env |
--cdp-header <headers...> | CDP headers to send with the connect request, multiple can be specified.env |
--cdp-timeout | timeout in milliseconds for connecting to CDP endpoint, defaults to 30000msenv |
--codegen | specify the language to use for code generation, possible values: "typescript", "python", "java", "csharp", "none". Default is "typescript".env |
--config | path to the configuration file.env |
--console-level | level of console messages to return: "error", "warning", "info", "debug". Each level includes the messages of more severe levels.env |
--device | device to emulate, for example: "iPhone 15"env |
--mobile | emulate a generic mobile device (Pixel 10 for Chromium, iPhone 17 for WebKit). Mobile pages are usually lighter, which saves tokens. Cannot be combined with --device.env |
--executable-path | path to the browser executable.env |
--extension | Connect to a running browser instance (Edge/Chrome only). Requires the "Playwright Extension" to be installed.env |
--endpoint | Bound browser endpoint to connect to.env |
--grant-permissions <permissions...> | List of permissions to grant to the browser context, for example "geolocation", "clipboard-read", "clipboard-write".env |
--headless | run browser in headless mode, headed by defaultenv |
--host | host to bind server to. Default is localhost. Use 0.0.0.0 to bind to all interfaces.env |
--ignore-https-errors | ignore https errorsenv |
--init-page <path...> | path to TypeScript file to evaluate on Playwright page objectenv |
--init-script <path...> | path to JavaScript file to add as an initialization script. The script will be evaluated in every page before any of the page's scripts. Can be specified multiple times.env |
--isolated | keep the browser profile in memory, do not save it to disk.env |
--image-responses | whether to send image responses to the client. Can be "allow" or "omit", Defaults to "allow".env |
--no-sandbox | disable the sandbox for all process types that are normally sandboxed.env |
--output-dir | path to the directory for output files.env |
--output-max-size | Threshold for evicting old output files, in bytes.env |
--port | port to listen on for SSE transport.env |
--proxy-bypass | comma-separated domains to bypass proxy, for example ".com,chromium.org,.domain.com"env |
--proxy-server | specify proxy server, for example "http://myproxy:3128" or "socks5://myproxy:8080"env |
--sandbox | enable the sandbox for all process types that are normally not sandboxed.env |
--save-session | Whether to save the Playwright MCP session into the output directory.env |
--secrets | path to a file containing secrets in the dotenv formatenv |
--shared-browser-context | reuse the same browser context between all connected HTTP clients.env |
--snapshot-boxes | include each element's bounding box as [box=x,y,width,height] in snapshots. Coordinates are viewport-relative, in CSS pixels.env |
--snapshot-mode | when taking snapshots for responses, specifies the mode to use. Can be "full" or "none". Default is "full".env |
--storage-state | path to the storage state file for isolated sessions.env |
--test-id-attribute | specify the attribute to use for test ids, defaults to "data-testid"env |
--timeout-action | specify action timeout in milliseconds, defaults to 5000msenv |
--timeout-navigation | specify navigation timeout in milliseconds, defaults to 60000msenv |
--timeout-settle | how long to wait after each action for triggered work to settle, in milliseconds, defaults to 500msenv |
--user-agent | specify user agent stringenv |
--user-data-dir | path to the user data directory. If not specified, a temporary directory will be created.env |
--viewport-size | specify browser viewport size in pixels, for example "1280x720"env |
You can run Playwright MCP with persistent profile like a regular browser (default), in isolated contexts for testing sessions, or connect to your existing browser using the browser extension.
Persistent profile
All the logged in information will be stored in the persistent profile, you can delete it between sessions if you'd like to clear the offline state.
Persistent profile is located at the following locations and you can override it with the --user-data-dir argument.
# Windows
%USERPROFILE%\AppData\Local\ms-playwright\mcp-{channel}-{workspace-hash}
# macOS
- ~/Library/Caches/ms-playwright/mcp-{channel}-{workspace-hash}
# Linux
- ~/.cache/ms-playwright/mcp-{channel}-{workspace-hash}{workspace-hash} is derived from the MCP client's workspace root, so different projects get separate profiles automatically.
A persistent profile can only be used by one browser instance at a time, so concurrent MCP clients sharing the same workspace will conflict. To run several clients in parallel, start each additional client with--isolated or point it at a distinct --user-data-dir.
Isolated
In the isolated mode, each session is started in the isolated profile. Every time you ask MCP to close the browser,
the session is closed and all the storage state for this session is lost. You can provide initial storage state
to the browser via the config's contextOptions or via the --storage-state argument. Learn more about the storage
state here.
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest",
"--isolated",
"--storage-state={path/to/storage.json}"
]
}
}
}Browser Extension
The Playwright MCP Chrome Extension allows you to connect to existing browser tabs and leverage your logged-in sessions and browser state. See microsoft/playwright › packages/extension for installation and setup instructions.
There are multiple ways to provide the initial state to the browser context or a page.
For the storage state, you can either:
Start with a user data directory using the --user-data-dir argument. This will persist all browser data between the sessions.
Start with a storage state file using the --storage-state argument. This will load cookies and local storage from the file into an isolated browser context.
For the page state, you can use:
--init-page to point to a TypeScript file that will be evaluated on the Playwright page object. This allows you to run arbitrary code to set up the page.
// init-page.ts
export default async ({ page }) => {
await page.context().grantPermissions(['geolocation']);
await page.context().setGeolocation({ latitude: 37.7749, longitude: -122.4194 });
await page.setViewportSize({ width: 1280, height: 720 });
};--init-script to point to a JavaScript file that will be added as an initialization script. The script will be evaluated in every page before any of the page's scripts.
This is useful for overriding browser APIs or setting up the environment.
// init-script.js
window.isPlaywrightMCP = true;The Playwright MCP server can be configured using a JSON configuration file. You can specify the configuration file
using the --config command line option:
npx @playwright/mcp@latest --config path/to/config.json{
/**
* The browser to use.
*/
browser?: {
/**
* The type of browser to use.
*/
browserName?: 'chromium' | 'firefox' | 'webkit';
/**
* Keep the browser profile in memory, do not save it to disk.
*/
isolated?: boolean;
/**
* Path to a user data directory for browser profile persistence.
* Temporary directory is created by default.
*/
userDataDir?: string;
/**
* Launch options passed to
* @see https://playwright.dev/docs/api/class-browsertype#browser-type-launch-persistent-context
*
* This is useful for settings options like `channel`, `headless`, `executablePath`, etc.
*/
launchOptions?: playwright.LaunchOptions;
/**
* Context options for the browser context.
*
* This is useful for settings options like `viewport`.
*/
contextOptions?: playwright.BrowserContextOptions;
/**
* Chrome DevTools Protocol endpoint to connect to an existing browser instance in case of Chromium family browsers.
*/
cdpEndpoint?: string;
/**
* CDP headers to send with the connect request.
*/
cdpHeaders?: Record<string, string>;
/**
* Timeout in milliseconds for connecting to CDP endpoint. Defaults to 30000 (30 seconds). Pass 0 to disable timeout.
*/
cdpTimeout?: number;
/**
* Remote endpoint to connect to an existing Playwright server. May be a
* WebSocket URL string, or a [ConnectOptions] object that mirrors the
* `connectOptions` shape used by the test runner. When passed as an object,
* `exposeNetwork`, `headers`, `slowMo`, and `timeout` are forwarded to the
* underlying connect call.
*/
remoteEndpoint?: string | playwright.ConnectOptions & { endpoint: string };
/**
* Paths to TypeScript files to add as initialization scripts for Playwright page.
*/
initPage?: string[];
/**
* Paths to JavaScript files to add as initialization scripts.
* The scripts will be evaluated in every page before any of the page's scripts.
*/
initScript?: string[];
},
/**
* Connect to a running browser instance (Edge/Chrome only). If specified, `browser`
* config is ignored.
* Requires the "Playwright Extension" to be installed.
*/
extension?: boolean;
server?: {
/**
* The port to listen on for SSE or MCP transport.
*/
port?: number;
/**
* The host to bind the server to. Default is localhost. Use 0.0.0.0 to bind to all interfaces.
*/
host?: string;
/**
* The hosts this server is allowed to serve from. Defaults to the host server is bound to.
* This is not for CORS, but rather for the DNS rebinding protection.
*/
allowedHosts?: string[];
},
/**
* List of enabled tool capabilities. Possible values:
* - 'core': Core browser automation features.
* - 'pdf': PDF generation and manipulation.
* - 'vision': Coordinate-based interactions.
* - 'devtools': Developer tools features.
*/
capabilities?: ToolCapability[];
/**
* Whether to save the Playwright session into the output directory.
*/
saveSession?: boolean;
/**
* Reuse the same browser context between all connected HTTP clients.
*/
sharedBrowserContext?: boolean;
/**
* Secrets are used to replace matching plain text in the tool responses to prevent the LLM
* from accidentally getting sensitive data. It is a convenience and not a security feature,
* make sure to always examine information coming in and from the tool on the client.
*/
secrets?: Record<string, string>;
/**
* The directory to save output files.
*/
outputDir?: string;
/**
* Threshold for evicting old output files, in bytes.
*/
outputMaxSize?: number;
console?: {
/**
* The level of console messages to return. Each level includes the messages of more severe levels. Defaults to "info".
*/
level?: 'error' | 'warning' | 'info' | 'debug';
},
network?: {
/**
* List of origins to allow the browser to request. Default is to allow all. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
*
* Supported formats:
* - Full origin: `https://example.com:8080` - matches only that origin
* - Wildcard port: `http://localhost:*` - matches any port on localhost with http protocol
*/
allowedOrigins?: string[];
/**
* List of origins to block the browser to request. Origins matching both `allowedOrigins` and `blockedOrigins` will be blocked.
*
* Supported formats:
* - Full origin: `https://example.com:8080` - matches only that origin
* - Wildcard port: `http://localhost:*` - matches any port on localhost with http protocol
*/
blockedOrigins?: string[];
};
/**
* Specify the attribute to use for test ids, defaults to "data-testid".
*/
testIdAttribute?: string;
timeouts?: {
/*
* Configures default action timeout: https://playwright.dev/docs/api/class-page#page-set-default-timeout. Defaults to 5000ms.
*/
action?: number;
/*
* Configures default navigation timeout: https://playwright.dev/docs/api/class-page#page-set-default-navigation-timeout. Defaults to 60000ms.
*/
navigation?: number;
/**
* Configures default expect timeout: https://playwright.dev/docs/test-timeouts#expect-timeout. Defaults to 5000ms.
*/
expect?: number;
/**
* How long to wait after each action for triggered work (navigations, requests) to settle before responding. Defaults to 500ms.
*/
settle?: number;
};
/**
* Whether to send image responses to the client. Can be "allow", "omit", or "auto". Defaults to "auto", which sends images if the client can display them.
*/
imageResponses?: 'allow' | 'omit';
snapshot?: {
/**
* When taking snapshots for responses, specifies the mode to use.
*/
mode?: 'full' | 'none';
/**
* Whether to include each element's bounding box as [box=x,y,width,height] in snapshots.
* Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect).
*/
boxes?: boolean;
};
/**
* allowUnrestrictedFileAccess acts as a guardrail to prevent the LLM from accidentally
* wandering outside its intended workspace. It is a convenience defense to catch unintended
* file access, not a secure boundary; a deliberate attempt to reach other directories can be
* easily worked around, so always rely on client-level permissions for true security.
*/
allowUnrestrictedFileAccess?: boolean;
/**
* Specify the language to use for code generation.
*/
codegen?: 'typescript' | 'python' | 'java' | 'csharp' | 'none';
}When running headed browser on system w/o display or from worker processes of the IDEs,
run the MCP server from environment with the DISPLAY and pass the --port flag to enable HTTP transport.
npx @playwright/mcp@latest --port 8931And then in MCP client config, set the url to the HTTP endpoint:
{
"mcpServers": {
"playwright": {
"url": "http://localhost:8931/mcp"
}
}
}Related MCP server: Playwright MCP
Playwright MCP is not a security boundary. See MCP Security Best Practices for guidance on securing your deployment.
NOTE: The Docker implementation only supports headless chromium at the moment.
{
"mcpServers": {
"playwright": {
"command": "docker",
"args": ["run", "-i", "--rm", "--init", "--pull=always", "mcr.microsoft.com/playwright/mcp"]
}
}
}Or If you prefer to run the container as a long-lived service instead of letting the MCP client spawn it, use:
docker run -d -i --rm --init --pull=always \
--entrypoint node \
--name playwright \
-p 8931:8931 \
mcr.microsoft.com/playwright/mcp \
/app/cli.js --headless --browser chromium --no-sandbox --port 8931 --host 0.0.0.0The server will listen on host port 8931 and can be reached by any MCP client.
You can build the Docker image yourself.
docker build -t mcr.microsoft.com/playwright/mcp .import http from 'http';
import { createConnection } from '@playwright/mcp';
import { SSEServerTransport } from '@modelcontextprotocol/sdk/server/sse.js';
http.createServer(async (req, res) => {
// ...
// Creates a headless Playwright MCP server with SSE transport
const connection = await createConnection({ browser: { launchOptions: { headless: true } } });
const transport = new SSEServerTransport('/messages', res);
await connection.connect(transport);
// ...
});browser_click
Title: Click
Description: Perform click on a web page
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string): Exact target element reference from the page snapshot, or a unique element selector
doubleClick (boolean, optional): Whether to perform a double click instead of a single click
button (string, optional): Button to click, defaults to left
modifiers (array, optional): Modifier keys to press
Read-only: false
browser_close
Title: Close browser
Description: Close the page
Parameters: None
Read-only: false
browser_console_messages
Title: Get console messages
Description: Returns all console messages
Parameters:
level (string): Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to "info".
all (boolean, optional): Return all console messages since the beginning of the session, not just since the last navigation. Defaults to false.
filename (string, optional): Filename to save the console messages to. If not provided, messages are returned as text.
Read-only: true
browser_drag
Title: Drag mouse
Description: Perform drag and drop between two elements
Parameters:
startElement (string, optional): Human-readable source element description used to obtain the permission to interact with the element
startTarget (string): Exact target element reference from the page snapshot, or a unique element selector
endElement (string, optional): Human-readable target element description used to obtain the permission to interact with the element
endTarget (string): Exact target element reference from the page snapshot, or a unique element selector
Read-only: false
browser_drop
Title: Drop files or data onto an element
Description: Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of "paths" or "data" must be provided.
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string): Exact target element reference from the page snapshot, or a unique element selector
paths (array, optional): Absolute paths to files to drop onto the element.
data (object, optional): Data to drop, as a map of MIME type to string value (e.g. {"text/plain": "hello", "text/uri-list": "https://example.com"}).
Read-only: false
browser_evaluate
Title: Evaluate JavaScript
Description: Evaluate JavaScript expression on page or element
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string, optional): Exact target element reference from the page snapshot, or a unique element selector
function (string): () => { /* code / } or (element) => { / code */ } when element is provided
filename (string, optional): Filename to save the result to. If not provided, result is returned as text.
Read-only: false
browser_file_upload
Title: Upload files
Description: Upload one or multiple files
Parameters:
paths (array, optional): The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.
Read-only: false
browser_fill_form
Title: Fill form
Description: Fill multiple form fields
Parameters:
fields (array): Fields to fill in
Read-only: false
browser_find
Title: Find in page snapshot
Description: Search the accessibility snapshot of the current page for text or a regular expression. Returns matching snapshot nodes with a few lines of surrounding context (like search snippets), each shown under its path from the root of the tree, which is cheaper than capturing the whole snapshot when you only need to locate an element and its ref.
Parameters:
text (string, optional): Plain text to search for in the page snapshot (case-insensitive substring match). Provide either text or regex, not both.
regex (string, optional): Regular expression to search for in the page snapshot. Matching is case-sensitive by default; wrap the pattern in slashes to add flags, e.g. "/error/i" for case-insensitive. Provide either text or regex, not both.
Read-only: true
browser_handle_dialog
Title: Handle a dialog
Description: Handle a dialog
Parameters:
accept (boolean): Whether to accept the dialog.
promptText (string, optional): The text of the prompt in case of a prompt dialog.
Read-only: false
browser_hover
Title: Hover mouse
Description: Hover over element on page
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string): Exact target element reference from the page snapshot, or a unique element selector
Read-only: false
browser_navigate
Title: Navigate to a URL
Description: Navigate to a URL
Parameters:
url (string): The URL to navigate to
Read-only: false
browser_navigate_back
Title: Go back
Description: Go back to the previous page in the history
Parameters: None
Read-only: false
browser_network_request
Title: Show network request details
Description: Returns full details (headers and body) of a single network request, or a single part if part is set. Use the number from browser_network_requests.
Parameters:
index (integer): 1-based index of the request, as printed by browser_network_requests.
part (string, optional): Return only this part of the request. Omit to return full details.
filename (string, optional): Filename to save the result to. If not provided, output is returned as text.
Read-only: true
browser_network_requests
Title: List network requests
Description: Returns a numbered list of network requests since loading the page. Use browser_network_request with the number to get full details.
Parameters:
static (boolean): Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false.
filter (string, optional): Only return requests whose URL matches this regexp (e.g. "/api/.*user").
filename (string, optional): Filename to save the network requests to. If not provided, requests are returned as text.
Read-only: true
browser_press_key
Title: Press a key
Description: Press a key on the keyboard
Parameters:
key (string): Name of the key to press or a character to generate, such as ArrowLeft or a
Read-only: false
browser_resize
Title: Resize browser window
Description: Resize the browser window
Parameters:
width (number): Width of the browser window
height (number): Height of the browser window
Read-only: false
browser_run_code_unsafe
Title: Run Playwright code (unsafe)
Description: Run a Playwright code snippet. Unsafe: executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent.
Parameters:
code (string, optional): A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: async (page) => { await page.getByRole('button', { name: 'Submit' }).click(); return await page.title(); }
filename (string, optional): Load code from the specified file. If both code and filename are provided, code will be ignored.
Read-only: false
browser_select_option
Title: Select option
Description: Select an option in a dropdown
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string): Exact target element reference from the page snapshot, or a unique element selector
values (array): Array of values to select in the dropdown. This can be a single value or multiple values.
Read-only: false
browser_snapshot
Title: Page snapshot
Description: Capture accessibility snapshot of the current page, this is better than screenshot
Parameters:
target (string, optional): Exact target element reference from the page snapshot, or a unique element selector
filename (string, optional): Save snapshot to markdown file instead of returning it in the response.
depth (number, optional): Limit the depth of the snapshot tree
boxes (boolean, optional): Include each element's bounding box as [box=x,y,width,height] in the snapshot. Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect)
Read-only: true
browser_take_screenshot
Title: Take a screenshot
Description: Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string, optional): Exact target element reference from the page snapshot, or a unique element selector
type (string, optional): Image format for the screenshot. If unset, inferred from the filename extension, otherwise png.
filename (string, optional): File name to save the screenshot to. Defaults to page-{timestamp}.{png|jpeg|webp} if not specified. Prefer relative file names to stay within the output directory.
fullPage (boolean, optional): When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
scale (string): Image resolution scale. "css" produces a screenshot sized in CSS pixels (smaller, consistent across devices). "device" produces a high-resolution screenshot using device pixels (larger, accounts for the device pixel ratio). Default is css.
Read-only: true
browser_type
Title: Type text
Description: Type text into editable element
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string): Exact target element reference from the page snapshot, or a unique element selector
text (string): Text to type into the element
submit (boolean, optional): Whether to submit entered text (press Enter after)
slowly (boolean, optional): 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.
Read-only: false
browser_wait_for
Title: Wait for
Description: Wait for text to appear or disappear or a specified time to pass
Parameters:
time (number, optional): The time to wait in seconds
text (string, optional): The text to wait for
textGone (string, optional): The text to wait for to disappear
Read-only: false
browser_tabs
Title: Manage tabs
Description: List, create, close, or select a browser tab.
Parameters:
action (string): Operation to perform
index (number, optional): Tab index, used for close/select. If omitted for close, current tab is closed.
url (string, optional): URL to navigate to in the new tab, used for new.
Read-only: false
browser_get_config
Title: Get config
Description: Get the final resolved config after merging CLI options, environment variables and config file.
Parameters: None
Read-only: true
browser_network_state_set
Title: Set network state
Description: Sets the browser network state to online or offline. When offline, all network requests will fail.
Parameters:
state (string): Set to "offline" to simulate offline mode, "online" to restore network connectivity
Read-only: false
browser_route
Title: Mock network requests
Description: Set up a route to mock network requests matching a URL pattern
Parameters:
pattern (string): URL pattern to match (e.g., "/api/users", "/*.{png,jpg}")
status (number, optional): HTTP status code to return (default: 200)
body (string, optional): Response body (text or JSON string)
contentType (string, optional): Content-Type header (e.g., "application/json", "text/html")
headers (array, optional): Headers to add in "Name: Value" format
removeHeaders (string, optional): Comma-separated list of header names to remove from request
Read-only: false
browser_route_list
Title: List network routes
Description: List all active network routes
Parameters: None
Read-only: true
browser_unroute
Title: Remove network routes
Description: Remove network routes matching a pattern (or all routes if no pattern specified)
Parameters:
pattern (string, optional): URL pattern to unroute (omit to remove all routes)
Read-only: false
browser_cookie_clear
Title: Clear cookies
Description: Clear all cookies
Parameters: None
Read-only: false
browser_cookie_delete
Title: Delete cookie
Description: Delete a specific cookie
Parameters:
name (string): Cookie name to delete
Read-only: false
browser_cookie_get
Title: Get cookie
Description: Get a specific cookie by name
Parameters:
name (string): Cookie name to get
Read-only: true
browser_cookie_list
Title: List cookies
Description: List all cookies (optionally filtered by domain/path)
Parameters:
domain (string, optional): Filter cookies by domain
path (string, optional): Filter cookies by path
Read-only: true
browser_cookie_set
Title: Set cookie
Description: Set a cookie with optional flags (domain, path, expires, httpOnly, secure, sameSite)
Parameters:
name (string): Cookie name
value (string): Cookie value
domain (string, optional): Cookie domain
path (string, optional): Cookie path
expires (number, optional): Cookie expiration as Unix timestamp
httpOnly (boolean, optional): Whether the cookie is HTTP only
secure (boolean, optional): Whether the cookie is secure
sameSite (string, optional): Cookie SameSite attribute
Read-only: false
browser_localstorage_clear
Title: Clear localStorage
Description: Clear all localStorage
Parameters: None
Read-only: false
browser_localstorage_delete
Title: Delete localStorage item
Description: Delete a localStorage item
Parameters:
key (string): Key to delete
Read-only: false
browser_localstorage_get
Title: Get localStorage item
Description: Get a localStorage item by key
Parameters:
key (string): Key to get
Read-only: true
browser_localstorage_list
Title: List localStorage
Description: List all localStorage key-value pairs
Parameters: None
Read-only: true
browser_localstorage_set
Title: Set localStorage item
Description: Set a localStorage item
Parameters:
key (string): Key to set
value (string): Value to set
Read-only: false
browser_sessionstorage_clear
Title: Clear sessionStorage
Description: Clear all sessionStorage
Parameters: None
Read-only: false
browser_sessionstorage_delete
Title: Delete sessionStorage item
Description: Delete a sessionStorage item
Parameters:
key (string): Key to delete
Read-only: false
browser_sessionstorage_get
Title: Get sessionStorage item
Description: Get a sessionStorage item by key
Parameters:
key (string): Key to get
Read-only: true
browser_sessionstorage_list
Title: List sessionStorage
Description: List all sessionStorage key-value pairs
Parameters: None
Read-only: true
browser_sessionstorage_set
Title: Set sessionStorage item
Description: Set a sessionStorage item
Parameters:
key (string): Key to set
value (string): Value to set
Read-only: false
browser_set_storage_state
Title: Restore storage state
Description: Restore storage state (cookies, local storage) from a file. This clears existing cookies and local storage before restoring.
Parameters:
filename (string): Path to the storage state file to restore from
Read-only: false
browser_storage_state
Title: Save storage state
Description: Save storage state (cookies, local storage) to a file for later reuse
Parameters:
filename (string, optional): File name to save the storage state to. Defaults to storage-state-{timestamp}.json if not specified.
Read-only: true
browser_annotate
Title: Annotate the current page
Description: Open the Playwright Dashboard in annotation mode for the current page and wait for the user to draw annotations. Returns the annotated screenshot, ARIA snapshot, and the list of annotations.
Parameters: None
Read-only: true
browser_hide_highlight
Title: Hide element highlight
Description: Remove a highlight overlay previously added for the element.
Parameters:
element (string, optional): Human-readable element description used when adding the highlight; must match the value passed to browser_highlight.
target (string, optional): Exact target element reference from the page snapshot, or a unique element selector
Read-only: true
browser_highlight
Title: Highlight element
Description: Show a persistent highlight overlay around the element on the page.
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string): Exact target element reference from the page snapshot, or a unique element selector
style (string, optional): Additional inline CSS applied to the highlight overlay, e.g. "outline: 2px dashed red".
Read-only: true
browser_resume
Title: Resume paused script execution
Description: Resume script execution after it was paused. When called with step set to true, execution will pause again before the next action.
Parameters:
step (boolean, optional): When true, execution will pause again before the next action, allowing step-by-step debugging.
location (string, optional): Pause execution at a specific :, e.g. "example.spec.ts:42".
Read-only: false
browser_start_tracing
Title: Start tracing
Description: Start trace recording
Parameters: None
Read-only: true
browser_start_video
Title: Start video
Description: Start video recording
Parameters:
filename (string, optional): Filename to save the video.
size (object, optional): Video size
Read-only: true
browser_stop_tracing
Title: Stop tracing
Description: Stop trace recording
Parameters: None
Read-only: true
browser_stop_video
Title: Stop video
Description: Stop video recording
Parameters: None
Read-only: true
browser_video_chapter
Title: Video chapter
Description: Add a chapter marker to the video recording. Shows a full-screen chapter card with blurred backdrop.
Parameters:
title (string): Chapter title
description (string, optional): Chapter description
duration (number, optional): Duration in milliseconds to show the chapter card
Read-only: true
browser_video_hide_actions
Title: Hide action overlays
Description: Stop annotating actions performed on the page.
Parameters: None
Read-only: true
browser_video_show_actions
Title: Show action overlays
Description: Annotate subsequent actions performed on the page with a callout that names the action and highlights the target element. Useful while video recording or screencasting.
Parameters:
duration (number, optional): How long each action annotation stays on screen, in milliseconds. Defaults to 500.
position (string, optional): Where to place the action title relative to the page. Defaults to top-right.
cursor (string, optional): Cursor decoration for pointer actions. "pointer" (default) animates a mouse pointer from the previous action point to the next one; "none" disables the cursor decoration.
Read-only: true
browser_mouse_click_xy
Title: Click
Description: Click mouse button at a given position
Parameters:
x (number): X coordinate
y (number): Y coordinate
button (string, optional): Button to click, defaults to left
clickCount (number, optional): Number of clicks, defaults to 1
delay (number, optional): Time to wait between mouse down and mouse up in milliseconds, defaults to 0
Read-only: false
browser_mouse_down
Title: Press mouse down
Description: Press mouse down
Parameters:
button (string, optional): Button to press, defaults to left
Read-only: false
browser_mouse_drag_xy
Title: Drag mouse
Description: Drag left mouse button to a given position
Parameters:
startX (number): Start X coordinate
startY (number): Start Y coordinate
endX (number): End X coordinate
endY (number): End Y coordinate
Read-only: false
browser_mouse_move_xy
Title: Move mouse
Description: Move mouse to a given position
Parameters:
x (number): X coordinate
y (number): Y coordinate
Read-only: false
browser_mouse_up
Title: Press mouse up
Description: Press mouse up
Parameters:
button (string, optional): Button to press, defaults to left
Read-only: false
browser_mouse_wheel
Title: Scroll mouse wheel
Description: Scroll mouse wheel
Parameters:
deltaX (number): X delta
deltaY (number): Y delta
Read-only: false
browser_pdf_save
Title: Save as PDF
Description: Save page as PDF
Parameters:
filename (string, optional): File name to save the pdf to. Defaults to page-{timestamp}.pdf if not specified. Prefer relative file names to stay within the output directory.
Read-only: true
browser_generate_locator
Title: Create locator for element
Description: Generate locator for the given element to use in tests
Parameters:
element (string, optional): Human-readable element description used to obtain permission to interact with the element
target (string): Exact target element reference from the page snapshot, or a unique element selector
Read-only: true
browser_verify_element_visible
Title: Verify element visible
Description: Verify element is visible on the page
Parameters:
role (string): ROLE of the element. Can be found in the snapshot like this: - {ROLE} "Accessible Name":
accessibleName (string): ACCESSIBLE_NAME of the element. Can be found in the snapshot like this: - role "{ACCESSIBLE_NAME}"
Read-only: false
browser_verify_list_visible
Title: Verify list visible
Description: Verify list is visible on the page
Parameters:
element (string): Human-readable list description
target (string): Exact target element reference that points to the list
items (array): Items to verify
Read-only: false
browser_verify_text_visible
Title: Verify text visible
Description: Verify text is visible on the page. Prefer browser_verify_element_visible if possible.
Parameters:
text (string): TEXT to verify. Can be found in the snapshot like this: - role "Accessible Name": {TEXT} or like this: - text: {TEXT}
Read-only: false
browser_verify_value
Title: Verify value
Description: Verify element value
Parameters:
type (string): Type of the element
element (string): Human-readable element description
target (string): Exact target element reference from the page snapshot
value (string): Value to verify. For checkbox, use "true" or "false".
Read-only: false
Perform click on a web page
| Name | Required | Description | Default |
|---|---|---|---|
| button | No | Button to click, defaults to left | |
| target | Yes | Exact target element reference from the page snapshot, or a unique element selector | |
| element | No | Human-readable element description used to obtain permission to interact with the element | |
| modifiers | No | Modifier keys to press | |
| doubleClick | No | Whether to perform a double click instead of a single click |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations include destructiveHint: true and readOnlyHint: false, which already disclose that the tool may have side effects. The description adds no additional behavioral context, such as potential navigation or permission requirements. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It is concise, though it omits many details. The schema fills the gaps, so the brevity is acceptable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is minimal for a tool with 5 parameters and many siblings. While schema and annotations provide valuable structured information, the description lacks usage context, side effects, and alternative mentions, making it adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage with descriptions for all five parameters. The description adds no extra meaning beyond the schema, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (click) and resource (web page). It is a specific verb+resource combination, but it does not differentiate from sibling tools like browser_hover or browser_type, lacking explicit scope or selector details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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, no prerequisites, and no conditions. It simply states the action, leaving the agent without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Close the page
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint and openWorldHint, but the description does not clarify the scope of 'close the page'—whether it closes only the current tab, the entire browser, or whether it is reversible. This ambiguity is a significant gap for a destructive action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only three words, achieving maximum conciseness and immediate clarity. Every word earns its place, and the structure is perfectly front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For such a simple tool, the description is mostly adequate, but the ambiguity about scope (page vs. browser) and lack of information about side effects or reversibility prevent it from being fully complete. The annotations partially compensate, but the description itself is minimal.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema carries no information. With no parameters to document, the description does not need to add parameter semantics, and the baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'close' with a clear resource 'the page', making the tool's purpose immediately obvious. It distinguishes naturally from sibling tools like browser_navigate or browser_click by describing a distinct action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For instance, it does not mention that navigating to another page might be preferable to closing the current page, nor any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns all console messages
| Name | Required | Description | Default |
|---|---|---|---|
| all | No | Return all console messages since the beginning of the session, not just since the last navigation. Defaults to false. | |
| level | Yes | Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to "info". | info |
| filename | No | Filename to save the console messages to. If not provided, messages are returned as text. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds little beyond the annotations. It omits critical behaviors such as level filtering (which includes more severe levels) and the distinction between messages since last navigation versus the whole session. The phrase 'all console messages' is inaccurate for non-default settings, though it does not contradict the readOnlyHint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no redundancy. However, it is so brief that it sacrifices useful context, making it less effective than a slightly longer description would be.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has moderate complexity with three parameters including an enum, but the description fails to mention the filename saving option, the severity level semantics, or what the return value looks like. With no output schema, the agent is left without essential context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the parameters are fully documented in the schema. The description adds no additional meaning or context about the parameters, aligning with the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns console messages, using a specific verb and resource. However, it does not distinguish this tool from siblings like browser_network_requests, and the word 'all' is slightly misleading given the 'all' parameter defaults to false.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. It does not mention filtering by level, saving to a file, or any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Perform drag and drop between two elements
| Name | Required | Description | Default |
|---|---|---|---|
| endTarget | Yes | Exact target element reference from the page snapshot, or a unique element selector | |
| endElement | No | Human-readable target element description used to obtain the permission to interact with the element | |
| startTarget | Yes | Exact target element reference from the page snapshot, or a unique element selector | |
| startElement | No | Human-readable source element description used to obtain the permission to interact with the element |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true, readOnlyHint=false, and openWorldHint=true. The description's 'drag and drop' action is consistent with these annotations but adds no extra behavioral context (e.g., triggering mouse events, potential side effects). It does not contradict annotations, so a score of 3 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, 'Perform drag and drop between two elements,' with no unnecessary words. It is front-loaded and immediately communicates the core action, earning a high score for conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 4 parameters but only a minimal description. However, the schema provides detailed parameter descriptions, and annotations cover safety and mutability. The description alone is thin but, combined with structured data, is minimally sufficient for a simple drag-and-drop action. It does not explain return values or edge cases, but for this complexity level, a 3 is fair.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with each parameter (startTarget, endTarget, startElement, endElement) having its own description. The tool description does not add any parameter-level meaning beyond the schema. Per the baseline rule, a high-coverage schema yields a 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Perform drag and drop between two elements' clearly states the action (drag and drop) and the resource (between two elements). It is specific and distinguishes from sibling tools like browser_drop (drop without drag) and browser_click (single click).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 such as browser_drop or browser_click. It lacks any exclusions, prerequisites, or context indicating when drag-and-drop is the appropriate action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of "paths" or "data" must be provided.
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | Data to drop, as a map of MIME type to string value (e.g. {"text/plain": "hello", "text/uri-list": "https://example.com"}). | |
| paths | No | Absolute paths to files to drop onto the element. | |
| target | Yes | Exact target element reference from the page snapshot, or a unique element selector | |
| element | No | Human-readable element description used to obtain permission to interact with the element |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false, so the safety profile is partially disclosed. The description adds the 'as if dragged from outside the page' simulation context and the requirement that at least one of 'paths' or 'data' must be provided. However, it does not disclose side effects, permissions, or what happens after the drop, so the added transparency is limited.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long and front-loaded with the core purpose. The second sentence adds a necessary constraint about parameters. Every word earns its place; there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description sufficiently explains the tool's behavior for a moderately complex action with nested objects. It covers the main action, the data types, and a key constraint, which is enough for an agent to invoke it. It lacks explicit guidance on return values or when to choose this over alternatives, but these are not critical for a drop operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers all four parameters with descriptions, giving a baseline of 3. The description adds a cross-parameter constraint—'At least one of "paths" or "data" must be provided'—which is not present in the schema's required list. This extra semantic clarifies the relationship between the parameters, going beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'Drop files or MIME-typed data onto an element, as if dragged from outside the page.' It specifies the resource (element), the input types (files or MIME-typed data), and the manner (as if dragged from outside), which distinguishes it from sibling tools like browser_drag or browser_file_upload.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use the tool—when needing to simulate dropping files or data from outside the page onto an element. It does not explicitly mention alternatives or when not to use it, but the unique 'outside the page' distinction gives enough contextual guidance for an agent to select it over similar tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Evaluate JavaScript expression on page or element
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Exact target element reference from the page snapshot, or a unique element selector | |
| element | No | Human-readable element description used to obtain permission to interact with the element | |
| filename | No | Filename to save the result to. If not provided, result is returned as text. | |
| function | Yes | () => { /* code */ } or (element) => { /* code */ } when element is provided |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds no behavioral context beyond the annotations. It does not disclose that evaluating JavaScript may have side effects, alter page state, or require permissions, even though annotations already flag destructiveness. The description is silent on what actually happens when the tool runs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It is concise and easy to parse, though it may be slightly too terse for a tool of this complexity, but it earns its place as a clear summary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (arbitrary JavaScript execution, destructive potential, no output schema), the description is incomplete. It lacks information about when to choose this tool over browser_run_code_unsafe, safety considerations, return behavior, or side effects. The description alone is not sufficient for an agent to use it correctly in varied contexts.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all four parameters. The description's phrase 'on page or element' provides a minimal hint that aligns with the target/element parameters but adds no meaningful semantics beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Evaluate' with the resource 'JavaScript expression on page or element', clearly conveying the tool's purpose. It is distinct from most sibling tools, though it does not explicitly differentiate itself from browser_run_code_unsafe, preventing a top score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives such as browser_run_code_unsafe. There is no mention of prerequisites, exclusions, or typical use cases, leaving the agent to infer usage solely from the purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Upload one or multiple files
| Name | Required | Description | Default |
|---|---|---|---|
| paths | No | The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds no behavioral context beyond the annotations. While annotations indicate destructiveHint=true and readOnlyHint=false, the description does not explain the implications of uploading files, such as triggering file selection dialogs or potential overwrites. It also omits the cancellation behavior mentioned in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that directly communicates the core functionality. It is front-loaded and contains no unnecessary words, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the tool's simplicity, the description lacks essential context. It does not explain return behavior, interaction with the page, or prerequisites. The cancellation behavior is only documented in the schema, not the description, leaving the overall picture incomplete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a complete description of the 'paths' parameter, including that omitting it cancels the file chooser. The tool description repeats no parameter details and adds no extra semantics. Given the high schema coverage, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Upload one or multiple files'. It includes a specific verb and resource, making the purpose evident. However, it does not distinguish itself from sibling tools, though no sibling appears to offer the same upload functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives, nor any mention of prerequisites such as needing a file input element on the page. The description only states what it does, not how to use it effectively.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fill multiple form fields
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | Fields to fill in |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation nature is conveyed. The description adds no extra behavioral context, such as permission requirements, side effects, or whether existing values are overwritten, but it does not contradict the annotations either. With annotations covering the safety profile, a 3 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single five-word sentence: 'Fill multiple form fields'. It has zero filler or redundancy and immediately communicates the core purpose, earning a top score for conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a complex nested schema that is well-documented, but the description offers no usage context, alternative references, or expected return behavior. With no output schema and minimal description, the context is only moderately complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% description coverage for the 'fields' parameter and its nested properties (name, type, value, target, element). The description itself adds nothing beyond the schema, so the baseline 3 is warranted.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Fill' with resource 'multiple form fields', clearly indicating a batch operation. It's distinguishable from siblings like browser_type (which likely fills a single field) but doesn't explicitly reference those alternatives. Overall, purpose is clear and specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no context on when to choose this tool over browser_type, browser_select_option, browser_click, or other sibling tools. There is also no mention of prerequisites or exclusions, leaving the usage guidance entirely absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the accessibility snapshot of the current page for text or a regular expression. Returns matching snapshot nodes with a few lines of surrounding context (like search snippets), each shown under its path from the root of the tree, which is cheaper than capturing the whole snapshot when you only need to locate an element and its ref.
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | Plain text to search for in the page snapshot (case-insensitive substring match). Provide either text or regex, not both. | |
| regex | No | Regular expression to search for in the page snapshot. Matching is case-sensitive by default; wrap the pattern in slashes to add flags, e.g. "/error/i" for case-insensitive. Provide either text or regex, not both. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond the readOnlyHint annotation: it explains the return format (matching nodes with surrounding context and paths) and the cost benefit. It does not contradict annotations and gives users clear expectations of the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with purpose, and every clause adds useful information (return format, context, cost comparison, parameter rules). There is no redundancy or fluff, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema, the description sufficiently explains what the tool returns and how it works. It mentions search context, paths, and the fact that it's cheaper than a full snapshot, making it operationally complete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes both parameters thoroughly, and the description further clarifies semantics: text is case-insensitive substring, regex is case-sensitive with flag syntax. It also reinforces the either/or constraint, adding value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches the accessibility snapshot for text or regex, with a specific verb and resource. It distinguishes itself from sibling tools like browser_snapshot by highlighting that it's cheaper and yields targeted context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says to use this tool when you only need to locate an element and its ref, contrasting with capturing the whole snapshot. It also provides the rule to provide either text or regex, not both, which is essential for correct invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Handle a dialog
| Name | Required | Description | Default |
|---|---|---|---|
| accept | Yes | Whether to accept the dialog. | |
| promptText | No | The text of the prompt in case of a prompt dialog. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds no behavioral detail beyond the annotations. Annotations already flag destructiveHint=true and readOnlyHint=false, but the description does not explain what 'handling' entails, potential side effects, or requirements like promptText. It neither contradicts nor enriches the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single vague phrase that under-specifies the tool. It is not a case of efficient brevity but rather a failure to convey necessary information; every word merely repeats the name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that handles browser dialogs, the description omits crucial context such as when a dialog appears, what happens when accept is true or false, and how promptText is used. The schema covers parameter names but not the overall usage context, leaving the agent under-informed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for both parameters ('accept' and 'promptText'), so the schema carries full parameter semantics. The description adds nothing, but with complete schema coverage, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Handle a dialog' simply restates the tool name and title, providing no specific verb or resource scope. It does not indicate whether the tool accepts, dismisses, or otherwise interacts with the dialog, nor does it distinguish it from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool relative to alternatives, such as when a JavaScript dialog blocks navigation or when to supply promptText. The description offers no context, exclusion criteria, or alternative tool suggestions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Hover over element on page
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | Exact target element reference from the page snapshot, or a unique element selector | |
| element | No | Human-readable element description used to obtain permission to interact with the element |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=false and destructiveHint=true, which is surprising for a hover action, but the description adds no context about side effects, timing, or whether hover can trigger navigation or state changes. The description does not go beyond the obvious act of hovering, leaving behavioral ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence with no wasted words, making it easy to scan. However, it is arguably too terse to fully convey the tool's purpose and usage context, though conciseness itself is strong.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple hover action, the description is minimal, but the annotations (destructiveHint=true) and lack of output schema create a need for additional behavioral context. The description does not explain what happens after hovering, potential delays, or failure conditions, leaving the agent under-informed for a tool that could have side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both 'target' and 'element' described in the schema. The description itself adds no parameter details, but because the schema fully documents parameters, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Hover over element on page' uses a specific verb (hover) and resource (element on page), clearly distinguishing it from sibling tools like browser_click, browser_drag, and browser_drop. It is immediately obvious what action this tool performs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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, such as when hovering is needed to trigger tooltips or reveal menus. No exclusions or prerequisites are mentioned, so an agent must infer usage solely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns full details (headers and body) of a single network request, or a single part if part is set. Use the number from browser_network_requests.
| Name | Required | Description | Default |
|---|---|---|---|
| part | No | Return only this part of the request. Omit to return full details. | |
| index | Yes | 1-based index of the request, as printed by browser_network_requests. | |
| filename | No | Filename to save the result to. If not provided, output is returned as text. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that the tool can return 'full details (headers and body)' or a single part when `part` is set, which is useful behavioral context beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. The first sentence conveys the core behavior and variable output, and the second provides the necessary prerequisite context. It is well-structured and easily scanned.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given three parameters, an enum, and no output schema, the description sufficiently explains return granularity and how to obtain the index. The filename parameter is not mentioned in the description, but the schema documents it, so the description remains adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description enhances the schema by explicitly defining 'full details' as 'headers and body' and reinforcing the index's origin in browser_network_requests, adding value beyond the schema's descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the specific action: 'Returns full details (headers and body) of a single network request,' using a clear verb and resource. It differentiates from the sibling browser_network_requests by specifying 'single' and referencing that tool's index.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The instruction 'Use the number from browser_network_requests' clearly implies a workflow: first list requests, then retrieve details by index. It provides context for when to use this tool but does not explicitly state when not to use it or name alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a numbered list of network requests since loading the page. Use browser_network_request with the number to get full details.
| Name | Required | Description | Default |
|---|---|---|---|
| filter | No | Only return requests whose URL matches this regexp (e.g. "/api/.*user"). | |
| static | Yes | Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false. | |
| filename | No | Filename to save the network requests to. If not provided, requests are returned as text. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only and non-destructive behavior. Description adds the temporal scope ('since loading the page') and return format (numbered list), which are useful behavioral details beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core purpose, and a concise pointer to the follow-up tool. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a listing tool with good annotations and full schema coverage, the description explains the output format and how to access details, which is complete enough for an agent to select and invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with detailed descriptions for filter, static, and filename. The description itself does not add parameter-specific information, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'Returns a numbered list of network requests since loading the page' with a specific verb and resource. It also distinguishes itself from the sibling browser_network_request by explicitly saying to use that tool for full details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clear context that this tool produces a list to browse, with an explicit instruction to use browser_network_request for full details. It does not list exclusions but the intended workflow is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Press a key on the keyboard
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Name of the key to press or a character to generate, such as `ArrowLeft` or `a` |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given that annotations already indicate destructiveHint=true, the description adds no extra behavioral context. It does not mention side effects like triggering shortcuts, submitting forms, or keydown/up events. The agent gains no insight beyond the name and annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is perfectly concise, though brevity comes at the cost of usefulness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool, the description is minimally adequate, especially with annotations and schema covering the basics. However, it fails to disambiguate from similar browser tools or mention any caveats, leaving the agent without full context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the parameter description ('Name of the key to press or a character to generate, such as ArrowLeft or a') is clear. The description does not add further parameter details, but the schema carries the burden adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action ('Press a key on the keyboard'), which is specific and distinct from siblings like browser_type (typing text) and browser_click. It lacks explicit differentiation from alternatives, but the verb+resource is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 browser_type, browser_fill_form, or other keyboard-related actions. There are no exclusions or contextual hints, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resize the browser window
| Name | Required | Description | Default |
|---|---|---|---|
| width | Yes | Width of the browser window | |
| height | Yes | Height of the browser window |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true, covering the safety profile. The description adds no extra behavioral context, such as how resizing affects the viewport or subsequent interactions. It meets the baseline but provides no additional value beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that is concise and complete. Every word contributes to the meaning, with no unnecessary detail or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with full schema coverage and no output schema, the description is mostly sufficient. However, it omits practical details such as units (pixels) and any constraints on values, leaving a small gap in completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both width and height parameters. The description does not add further meaning beyond what the schema provides (e.g., units like pixels or allowed ranges), so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'resize' with a clear resource 'browser window', effectively distinguishing it from sibling tools like browser_navigate or browser_take_screenshot. It directly states what the tool does with no ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The intended usage is clear: use this tool to adjust the browser window's dimensions. No explicit alternatives or exclusions are mentioned, but given that no sibling tool serves a similar purpose, this is acceptable. The context is sufficient for an agent to decide when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a Playwright code snippet. Unsafe: executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent.
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: `async (page) => { await page.getByRole('button', { name: 'Submit' }).click(); return await page.title(); }` | |
| filename | No | Load code from the specified file. If both code and filename are provided, code will be ignored. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explicitly discloses the critical behavioral trait of executing arbitrary JavaScript in the server process, adding the 'RCE-equivalent' warning beyond the annotations' destructiveHint. This provides meaningful context about the tool's power and risk, going beyond the structured annotation flags.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the primary purpose and followed immediately by a crucial safety warning. Every word earns its place, with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple structure (2 params, no output schema) and the presence of annotations and detailed schema, the description provides sufficient context for a risky tool. It covers purpose and danger, though it does not elaborate on return values or side effects, which are not critical given the schema's code example returns a value and the tool's open-ended nature.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage for parameters is 100%, with thorough descriptions in the schema itself (including a code example and semantics for filename precedence). The tool description adds no additional parameter-level meaning, so it sticks to the baseline of 3 for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('run') and resource ('Playwright code snippet'), and clearly distinguishes the tool from siblings by stating it executes arbitrary JavaScript in the Playwright server process, making it RCE-equivalent. This differentiates it from browser_evaluate or other browser-interaction tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives like browser_evaluate, but the 'unsafe' and 'RCE-equivalent' warning implies it is intended for advanced or unrestricted scenarios. Usage guidance is implied rather than explicit, so it falls short of providing clear when/when-not direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Select an option in a dropdown
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | Exact target element reference from the page snapshot, or a unique element selector | |
| values | Yes | Array of values to select in the dropdown. This can be a single value or multiple values. | |
| element | No | Human-readable element description used to obtain permission to interact with the element |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false, but the description adds no additional behavioral context such as side effects (e.g., triggering change events), permission requirements, or what happens with multiple values. The description does not contradict the annotations, but it fails to disclose anything beyond them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence with no unnecessary words. It is perfectly front-loaded and earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive browser interaction with no output schema, the description is too thin. It does not mention error scenarios, handling of multiple values, or the need for the target to be a select element. The schema and annotations are helpful, but the description leaves significant gaps for a tool that modifies page state.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has comprehensive descriptions for all three parameters, so the baseline is 3. The description adds no extra parameter meaning beyond clarifying the tool targets a dropdown, but this is marginal since the schema already covers the target and values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Select an option in a dropdown' clearly specifies the verb (select) and resource (option in a dropdown), distinguishing it from sibling interactions like browser_click or browser_type. It is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage context is implied by the tool name and description ('select' implies dropdowns), but there is no explicit guidance on when to use this vs. alternatives like clicking the dropdown, nor any exclusions or prerequisites. This mirrors the 'implied usage' level.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Capture accessibility snapshot of the current page, this is better than screenshot
| Name | Required | Description | Default |
|---|---|---|---|
| boxes | No | Include each element's bounding box as [box=x,y,width,height] in the snapshot. Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect) | |
| depth | No | Limit the depth of the snapshot tree | |
| target | No | Exact target element reference from the page snapshot, or a unique element selector | |
| filename | No | Save snapshot to markdown file instead of returning it in the response. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, establishing a safe, read-only operation. The description adds the fact that it captures an accessibility snapshot and is 'better than screenshot', hinting at a structured output, but it does not describe potential behavioral details like response size or whether the snapshot reflects dynamic DOM changes. No contradiction exists, but the additional value is limited.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded with the verb, making it efficient. However, it uses a comma splice and the comparative 'better' is vague, slightly reducing credibility. It is still concise and avoids unnecessary repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, and the description only says it captures an 'accessibility snapshot' without describing the return structure. However, the schema parameters (e.g., 'target' referencing 'the page snapshot') and annotations provide enough context for an agent to understand basic invocation and safety. It is minimally complete but lacks crucial output format details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All four parameters (boxes, depth, target, filename) have thorough descriptions in the schema, providing 100% coverage. The description itself does not mention any parameters or add meaning beyond the schema, so it sits at the baseline of 3 where the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the action ('Capture accessibility snapshot') and the resource ('current page'), and explicitly positions it against the screenshot sibling by claiming it is 'better than screenshot'. This distinguishes it from browser_take_screenshot. However, 'accessibility snapshot' is not defined, leaving some ambiguity about what the output contains, so it does not reach 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The only usage guidance is the comparative claim 'this is better than screenshot', which implies use over the screenshot tool. It does not specify scenarios where it should not be used or mention alternatives like browser_evaluate or browser_find. This is implied usage rather than explicit guidance, so it scores a 3.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List, create, close, or select a browser tab.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | URL to navigate to in the new tab, used for new. | |
| index | No | Tab index, used for close/select. If omitted for close, current tab is closed. | |
| action | Yes | Operation to perform |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate a destructive, open-world tool. The description adds the action list but discloses no additional behavioral traits like reversibility or side effects of closing/selecting tabs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, perfectly front-loaded, with zero filler. It directly states the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a multi-action tool with a complete schema and annotations, the brief description is adequate, though it does not describe return values for the list action or edge cases like omitted index for close. Still, given the simplicity, it's mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides full descriptions for all three parameters with 100% coverage, so the description adds no extra semantic detail beyond listing actions. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies four concrete operations (list, create, close, select) on browser tabs, clearly identifying a resource and a set of verbs. It distinguishes from sibling tools by focusing on tab management rather than navigation or page interaction, though it doesn't explicitly contrast with browser_close.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus browser_navigate or browser_close, and there are no stated conditions or alternatives. The description simply lists actions, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Image format for the screenshot. If unset, inferred from the filename extension, otherwise png. | |
| scale | Yes | Image resolution scale. "css" produces a screenshot sized in CSS pixels (smaller, consistent across devices). "device" produces a high-resolution screenshot using device pixels (larger, accounts for the device pixel ratio). Default is css. | css |
| target | No | Exact target element reference from the page snapshot, or a unique element selector | |
| element | No | Human-readable element description used to obtain permission to interact with the element | |
| filename | No | File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg|webp}` if not specified. Prefer relative file names to stay within the output directory. | |
| fullPage | No | When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey readOnlyHint=true and destructiveHint=false, so the description adds value by disclosing a behavioral limitation: screenshots cannot be used as a basis for performing actions. This is contextual information beyond the structured annotations, though it does not detail output format or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the primary purpose and immediately followed by a critical usage warning. Every word earns its place; there is no redundancy or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (6 parameters, no output schema) and rich annotations, the description covers the core purpose and a key limitation. It does not explicitly state what the screenshot returns or where it is saved, but the schema's filename parameter and the tool's name make this context reasonably implied. The description is sufficiently complete for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides comprehensive descriptions for all six parameters, including enums and defaults, achieving 100% schema coverage. The tool description adds no additional parameter details, so the baseline score of 3 is appropriate since the schema carries the full burden.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Take a screenshot of the current page.' It uses a specific verb and resource, and distinguishes itself from sibling tools by explicitly pointing to browser_snapshot for actions, which prevents confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-not-to-use guidance: 'You can't perform actions based on the screenshot, use browser_snapshot for actions.' This names the alternative tool and clearly delineates when browser_take_screenshot is not appropriate, satisfying the highest bar for usage guidelines.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Type text into editable element
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to type into the element | |
| 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. | |
| submit | No | Whether to submit entered text (press Enter after) | |
| target | Yes | Exact target element reference from the page snapshot, or a unique element selector | |
| element | No | Human-readable element description used to obtain permission to interact with the element |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations already declaring destructiveHint=true and readOnlyHint=false, the description adds minimal behavioral context beyond the annotations. It merely states 'editable element' and does not disclose consequences like replacing existing text, triggering key handlers, or submission behavior. No contradiction with annotations, but also no added value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the core purpose. It is appropriately sized and contains no filler or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters and no output schema, the description is too sparse. It does not explain what happens after typing (e.g., whether focus is required, whether existing content is cleared, or how the 'submit' parameter affects behavior). Most of the burden falls on parameter descriptions, but the overall tool context remains incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with all five parameters having descriptions. The tool description itself adds no parameter details beyond what the schema provides, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Type text into editable element' uses a specific verb ('Type') and resource ('editable element'). It is not a tautology and is understandable on its own, though it does not explicitly differentiate from sibling tools like browser_fill_form or browser_press_key.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 does not mention exclusions, prerequisites, or when a different tool might be more appropriate. Usage is only implied by the tool's name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Wait for text to appear or disappear or a specified time to pass
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | The text to wait for | |
| time | No | The time to wait in seconds | |
| textGone | No | The text to wait for to disappear |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly and non-destructive behavior, so the description does not need to repeat that. It does add the three wait modes (appear, disappear, time), but it omits important details like what happens on timeout, behavior when no parameters are provided, or whether multiple conditions can be combined.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise, front-loaded with the action, and covers all core functionality without any fluff. Every word contributes to meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With all parameters optional and no output schema, the description leaves ambiguity about calling with no arguments or with conflicting conditions (e.g., text and textGone together). It does not clarify timeout behavior or default waiting time, making it adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes all three parameters with 100% coverage. The description essentially restates the same information without adding new meaning, such as parameter precedence or interactions. It earns the baseline 3 for schema coverage but adds no extra depth.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: waiting for text to appear, disappear, or a time to pass. It uses a specific verb ('Wait') and describes the three distinct conditions, distinguishing it from sibling browser action tools like click or navigate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly conveys when to use this tool: when you need to wait for a page state or a fixed delay. There are no explicit exclusions or mentions of alternatives, but no sibling tool provides waiting functionality, so the usage context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.0.79browser_clickbrowser_closebrowser_console_messagesbrowser_dragbrowser_dropbrowser_evaluatebrowser_file_uploadbrowser_fill_formbrowser_findbrowser_handle_dialogbrowser_hoverbrowser_navigatebrowser_navigate_backbrowser_network_requestbrowser_network_requestsbrowser_press_keybrowser_resizebrowser_run_code_unsafebrowser_select_optionbrowser_snapshotbrowser_tabsbrowser_take_screenshotbrowser_typebrowser_wait_forEach tool targets a distinct browser action or resource. Overlapping operations like browser_type vs browser_fill_form are clearly differentiated by scope (single element vs multiple fields), and browser_snapshot vs browser_take_screenshot explicitly separate accessibility tree captures from visual screenshots. No two tools present meaningful ambiguity.
All tools share the 'browser_' prefix followed by a clear verb or verb phrase, using consistent snake_case throughout (e.g., browser_navigate, browser_fill_form, browser_network_request). Even multi-word names like browser_run_code_unsafe remain readable and predictable.
24 tools is above the typical 15-tool sweet spot, but the browser automation domain requires diverse actions including navigation, interaction, network inspection, dialogs, and tab management. Each tool earns its place, and the count feels slightly heavy but justified rather than bloated.
The tool set covers core browser workflows: navigate, interact (click/type/hover/select/drag/drop), wait, snapshot/screenshot, evaluate, handle dialogs, file upload, and network/console inspection. A few minor gaps exist, such as no explicit 'browser_forward' or 'browser_reload', but these can be worked around via navigation or evaluation.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Hosted browser for AI agents: screenshots, post-JS DOM, console, WCAG. No install, no API key.
Browser-backed QA with evidence and fix-ready reports for coding agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/J0from/oss-playwright-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
