Skip to main content
Glama

act

Perform a browser action like click, type, scroll, or navigate, then get back exactly what changed or a new view. Use it to drive real pages step by step with mouse and key events.

Instructions

Perform one action in a browser started with start_browser and get back what changed (~ changed, + added, - removed), or a new view after a navigation. Input is sent as real mouse and key events. Name the element by id from observe, or by role and name, or click a point with x and y. The first line of the answer says failed, blocked, challenge or stale when the action did not go through. stale: the ids are from a view that no longer exists, nothing was done, and a new view follows.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "browser_id": "<browser_id>",
      "action": "<action>"
    },
    "name": "act"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoclick: a viewport point instead of an element (with y).
yNo
dyNoscroll: pixels, positive is down.
idNoTarget element id, from observe.
msNowait: a fixed time in milliseconds, at most 30000.
toNoscroll.
forNowait: for text to appear, an element to go, or the URL to change.
tabNoTab id. Default: the tab used last.
urlNonavigate.
keysNopress: Enter, Escape, Control+A, or a sequence such as "Tab Tab Enter".
nameNo
roleNoWith name: the first element with this role and name, instead of id.
textNotype: the text. wait for text: the text. dialog: the prompt answer.
clearNotype: empty the field first.
filesNoupload: file paths on the browser's machine.
rightNoclick: right button.
acceptNodialog: accept (true) or dismiss.
actionYes
doubleNoclick: double click.
optionNoselect: option text or value.
submitNotype: press Enter afterwards.
timeoutNowait: milliseconds, default 10000, at most 30000.
browser_idYesThe id returned by start_browser.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.1/5.0
Behavior4/5

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

No annotations exist, so the description carries the full load and does well: it discloses that input is dispatched as real mouse/key events, defines the diff notation in the response, and enumerates the failure first-line markers (failed, blocked, challenge, stale). The stale case is explained precisely — ids from a dead view, nothing executed, new view follows. It omits timing/retry behavior and any permission or rate-limit context.

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?

Front-loaded with the action and the return contract, then targeting, then failure markers — a logical order with little waste. The diff-notation parenthetical and the compressed "stale:" clause are terse to the point of requiring a second read, which keeps it just short of a 5.

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?

For a 23-parameter, 15-action tool with no output schema and no annotations, the description covers the essentials an agent needs: prerequisite browser, targeting modes, return shape, and failure semantics. Gaps are secondary — tab selection behavior, blocking/timeout expectations, and what a challenge state implies for recovery.

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

Parameters3/5

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

Schema coverage is 87%, so the schema already documents nearly every field including x/y, role/name, and the action enum. The description adds the targeting-strategy relationship between id, role+name, and x/y, but contributes no syntax or constraint detail beyond that. Baseline 3 is appropriate.

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?

States a specific verb and resource ("Perform one action in a browser"), scopes it to a browser created by start_browser, and describes what comes back (a diff of changed/added/removed, or a new view after navigation). An agent can tell this apart from observe or start_browser from the description alone.

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?

Explicitly requires a browser from start_browser and gives three alternative targeting strategies (id from observe, role+name, or x/y point), which is real routing guidance. It does not, however, say when to prefer observe over act for reading state, nor any exclusion conditions.

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