Skip to main content
Glama

fl_act

Run multiple browser actions in one call to fill forms, click, submit, wait, and extract data, then get a fresh snapshot back.

Instructions

Run SEVERAL actions in one call (fill a whole form, click, submit, wait, extract) and get one fresh snapshot back. Always batch as many actions as possible: one call beats ten.

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": {
      "tab": "<tab>",
      "actions": "<actions>"
    },
    "name": "fl_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxNoMax interactive elements listed (default 150).
tabYes
textNoCharacters of page text to include (default 600, 0 for none).
actionsYes
snapshotNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv1.2.1
    • addedInput schema / properties / actions / items / properties / accept
      Added value: +{
      +  "description": "dialog: true to accept (OK), false to dismiss. value is the prompt answer.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / actions / items / properties / count
      Added value: +{
      +  "description": "mouse: 2 for a double click.",
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
    • addedInput schema / properties / actions / items / properties / do / description
      Added value: +"upload: files into a file input, or a button / drop zone that opens the file chooser. mouse: click at x,y (escape hatch for canvas, shadow DOM, extension overlays). dialog: how to answer the NEXT alert/confirm/prompt (default dismiss). resize: viewport width x height."
    • changedInput schema / properties / actions / items / properties / do / enum
      Previous value: -[
      -  "click",
      -  "dblclick",
      -  "hover",
      -  "fill",
      -  "type",
      -  "select",
      -  "check",
      -  "uncheck",
      -  "press",
      -  "download",
      -  "goto",
      -  "back",
      -  "wait",
      -  "scroll",
      -  "eval",
      -  "request"
      -]New value: +[
      +  "click",
      +  "dblclick",
      +  "hover",
      +  "fill",
      +  "type",
      +  "select",
      +  "check",
      +  "uncheck",
      +  "press",
      +  "download",
      +  "upload",
      +  "goto",
      +  "back",
      +  "wait",
      +  "scroll",
      +  "eval",
      +  "request",
      +  "mouse",
      +  "dialog",
      +  "resize"
      +]
    • addedInput schema / properties / actions / items / properties / files
      Added value: +{
      +  "description": "upload: absolute file paths. With var, a single file becomes {{var}}.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / actions / items / properties / height
      Added value: +{
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
    • addedInput schema / properties / actions / items / properties / width
      Added value: +{
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
    • addedInput schema / properties / actions / items / properties / x
      Added value: +{
      +  "description": "mouse: x in CSS pixels of the viewport, same scale as fl_screenshot.",
      +  "type": "number"
      +}
    • addedInput schema / properties / actions / items / properties / y / description
      Added value: +"mouse: y in CSS pixels. scroll: pixels to scroll (default 800)."
  2. First observedv1.1.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses that one fresh snapshot is returned, but does not explain side effects, action ordering, failure handling, partial execution, permissions, or destructive potential for actions like click, upload, goto, eval, and request.

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

Conciseness5/5

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

Two short sentences with zero filler and the batching instruction front-loaded. Every sentence earns its place and quickly conveys the main calling pattern.

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

Completeness2/5

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

The tool is complex: a nested actions array with many action types and fields, five top-level parameters, no output schema, and no annotations. The description is far too terse to cover execution semantics, failure behavior, tab handling, snapshot options, or how the many action types interact.

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

Parameters2/5

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

Schema description coverage is only 40%, and the description adds little meaning beyond the schema. It does not explain the required tab parameter, the snapshot flag, or the overall actions structure, and its mention of "extract" does not match the action enum.

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

Purpose4/5

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

States a specific verb and resource: run several browser actions in one call and return a fresh snapshot. The batching purpose is clear, but the description does not explicitly distinguish it from nearby tools such as fl_run, fl_run_many, or fl_flow.

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?

Gives clear usage guidance: batch as many actions as possible because one call beats ten, with examples like filling a whole form and submitting. It lacks explicit when-not-to-use guidance or named alternatives for single-action versus multi-action execution.

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