Skip to main content
Glama
cdp-bridge
by Unagi-cq

browser_act

Click or fill a specific browser control using a reference and page revision from browser_observe; if the reference is stale, re-observe the page and try again.

Instructions

Click or fill one control returned by browser_observe.

Args: tab_id: Tab ID returned by browser_observe. page_revision: Revision returned by browser_observe. ref: Control reference returned by browser_observe. action: Either "click" or "fill". value: Text to enter for "fill".

References are single-use and expire after 60 seconds. A stale result means the page or target changed; call browser_observe again.

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_id": "<tab_id>",
      "page_revision": "<page_revision>",
      "ref": "<ref>",
      "action": "<action>"
    },
    "name": "browser_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYes
valueNo
actionYes
tab_idYes
page_revisionYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.25

TDQS

A3.7/5.0
Behavior3/5

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

No annotations exist, so the description carries the full behavioral burden. It does disclose the most important trait: references are single-use and expire after 60 seconds. That is exactly the kind of context annotations would otherwise supply. The description also does not state the side effects of a click, such as navigation or form submission, whether a fill triggers events or submits, or what the output schema returns beyond the raw structure. A 3 reflects a solid disclosure of the reference lifecycle that is offset by the absence of any description of mutation 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.

Conciseness4/5

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

It is front-loaded with the purpose sentence, then a compact argument list, then the expiry and recovery rules. Every sentence earns its place. Repeating 'returned by browser_observe' for three parameters is slightly redundant, but it is defensible because it establishes the shared provenance.

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

Completeness5/5

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

This is a mutation tool with no annotations, and an output schema exists, so the description does not need to explain return values. It covers what is mutated, the valid action set, the lifecycle of the reference, and the recovery path when the reference is stale, which is the single failure mode an agent is most likely to hit. Enough is present for an agent to call the tool correctly and handle errors.

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 alone defines the five parameters. It identifies each: tab_id, page_revision, and ref all come from browser_observe; action is limited to click or fill; and value is the text entered only for fill. That is meaningful added value over the bare schema, where action has no enum and value has only a default of empty string. It could go further by stating the expected format of tab_id and page_revision, but the provenance, namely that both are returned by browser_observe, is the important part.

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?

The description opens with a specific verb and resource: 'Click or fill one control returned by browser_observe.' That single sentence tells an agent exactly what the tool mutates and where the target comes from, and it implicitly separates the tool from browser_observe, which only reads. It does not distinguish this tool from browser_batch or browser_execute_js, which could plausibly also act on a page.

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?

The description gives strong recovery guidance: when a reference is stale because the page or target changed, call browser_observe again. That also reinforces the intended observe-then-act loop. It never says when to choose this tool over browser_batch or browser_execute_js, and it never states preconditions such as the tab needing focus.

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