Skip to main content
Glama
chrome-remote-debugging-mcp

chrome-remote-debugging-mcp

by danilin-em

browse_act

Batch multiple browser actions like click, type, scroll, and wait into one call, then return the resulting page view. Stops at first failure so you can see where the page ended up.

Instructions

Run several actions against the current view, then return one new view.

Each action is a dict with a do key:

  • {"do": "click", "ref": 3}

  • {"do": "type", "ref": 2, "text": "коты", "clear": false}

  • {"do": "press", "key": "Enter"}

  • {"do": "select", "ref": 5, "value": "два"}

  • {"do": "check", "ref": 9} / {"do": "uncheck", "ref": 9}

  • {"do": "scroll", "ref": 7} or {"do": "scroll", "to": "bottom"}

  • {"do": "hover", "ref": 4}

  • {"do": "wait_for", "text": "Результаты", "timeout": 5} or {"do": "wait_for", "ref_gone": 3}

Refs come from the most recent browse or browse_view on this tab and are invalid afterwards. The batch stops at the first failure; a view is returned either way so you can see where the page ended up.

Returns {"tab_id", "steps", "view", "refs"}, plus "error" when a step failed, or {"error": ...} when the tab could not be resolved.

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": {
      "actions_list": "<actions_list>",
      "tab_id": "<tab_id>"
    },
    "name": "browse_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
tab_idYes
actions_listYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.1

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries real weight and does so well: it discloses that the batch stops at the first failure, that a view is returned regardless so you can see where the page ended up, and that refs are invalidated after the next browse/browse_view. It also spells out the exact return keys including the error shapes. It stops short of noting that actions like click/type can submit forms and cause irreversible state changes, which matters for a mutation-capable tool.

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?

Front-loaded with the one-sentence summary, then a compact bullet list of action shapes, then the lifecycle and return contract in two short paragraphs. Given that the schema documents nothing, every example line earns its place and nothing is redundant.

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 two-parameter tool with no output schema and no annotations, the description covers the return shape, error modes, ref lifetime, and all action variants. The remaining gaps are modest: tab_id semantics and what to do after a mid-batch failure (are remaining steps lost, must the caller rebuild the batch?) are left implicit.

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?

Schema description coverage is 0%, so the description must supply meaning — and it does, enumerating eight 'do' variants with their fields (ref, text, clear, value, key, timeout, to, ref_gone) and showing both scroll and wait_for forms. The gap is tab_id, which is never described beyond the phrase 'on this tab'; an agent must infer that it identifies the target tab.

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?

Opens with a specific verb and resource: 'Run several actions against the current view, then return one new view.' That clearly separates it from browse_view (read a view) and navigate (single navigation), and the ref-provenance line ties it to browse/browse_view. It never names a sibling as the alternative for a given case, which keeps it just short of a 5.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the batch model suggests you should group multiple interactions into one call instead of many calls, and the first-failure semantics tells you how batching behaves. There is no explicit 'use this when…' or 'do not use this for…' guidance, and no stated alternative for a single action.

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