Skip to main content
Glama

Browser Action

act

Perform browser actions like click, fill, and type using element references or CSS selectors. Returns updated page state after interactions.

Instructions

Perform a browser interaction: click, fill, type, check, select, press key, scroll, hover, mousemove, drag, upload, resize, back, forward. Use @eN refs from navigate/snapshot as the target (e.g. '@e2'). CSS selectors also work. drag: requires target (source) and target2 (destination). upload: requires target (file input) and filePaths. resize: requires width and height (no target needed). holdDuration: for click, holds mouse down for N ms (long-press). Returns a fresh snapshot if the page navigated, or just the action result if it didn't.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sessionIdYesSession ID.
actionYesInteraction to perform.
targetNo@eN ref or CSS selector. Required for click, fill, type, check, select, hover.
valueNoText for fill/type, option value for select.
keyNoKey name for press (e.g. 'Enter', 'Tab', 'Control+a').
scrollDirectionNoScroll direction. Default: down.
scrollAmountNoPixels to scroll. Default: 300.
typeDelayNoDelay in ms between keystrokes for action='type'. Enables human-like typing speed.
xNoX coordinate for mousemove action.
yNoY coordinate for mousemove action.
target2NoDrop destination for drag action. @eN ref or CSS selector.
filePathsNoFile path(s) for upload action. Single string or array of strings.
widthNoViewport width for resize action.
heightNoViewport height for resize action.
holdDurationNoHold duration in ms for click action (long-press). Uses mouse.down() + wait + mouse.up().
Behavior3/5

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

No annotations are provided, so the description carries full behavioral disclosure. It mentions return behavior (fresh snapshot vs. action result) and holdDuration details, but lacks description of side effects or prerequisites like active session.

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

Conciseness4/5

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

The description is organized: purpose first, then targeting guidance, then per-action specifics. It is relatively concise for the tool's complexity, though some redundancy could be trimmed (e.g., 'CSS selectors also work' is mentioned in parameters).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 15 parameters and no output schema, the description covers key behaviors and special actions. It does not explain sessionId or how to obtain @eN refs, but these are covered by sibling tools. Overall, it is sufficiently complete for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with per-parameter descriptions. The description adds value by clarifying relationships (e.g., target as source for drag, no target needed for resize) and explaining @eN refs, going beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Perform a browser interaction' and enumerates specific actions (click, fill, type, etc.). It distinguishes itself from sibling tools like navigate and snapshot by focusing on post-navigation interactions.

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

Usage Guidelines4/5

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

The description provides context for using @eN refs from navigate/snapshot, and specifies when to use target and target2 for drag, or filePaths for upload. However, it does not explicitly state when not to use this tool or mention alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/anthonybono21-cloud/leapfrog'

If you have feedback or need assistance with the MCP directory API, please join our Discord server