Skip to main content
Glama
Sign In
Antigravity Browser Operator

Antigravity Browser Operator

by hashan-lakshitha
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

browser_get_dom

Extracts a tab’s title, URL, compact DOM, indexed interactive elements with refs, and clean text so agents can inspect page structure and choose actions.

Instructions

Extracts the page title, URL, token-dense compact DOM representation, indexed interactive elements with refs, and clean text of the tab.

Input Schema

NameRequiredDescriptionDefault
tabIdNoOptional tab ID.
includeLinksNoWhether to include standalone links array (defaults to false as elements already index links).
maxTextLengthNoMaximum characters of body text to extract (defaults to 3000 to save tokens).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.0
    • addedInput schema / properties / includeLinks
      Added value: +{
+  "description": "Whether to include standalone links array (defaults to false as elements already index links).",
+  "type": "boolean"
+}
    • addedInput schema / properties / maxTextLength
      Added value: +{
+  "description": "Maximum characters of body text to extract (defaults to 3000 to save tokens).",
+  "type": "number"
+}
  2. First observedv1.0.1

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden. It implies a read-only extraction but never says so, and it omits how the tab is resolved when tabId is absent, what happens if the tab is closed or still loading, and how the text truncation interacts with the returned DOM.

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?

A single front-loaded sentence with no filler; every clause names a distinct output artifact. It is dense but readable, and nothing is wasted.

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?

With no output schema, the description does the necessary work of enumerating the return payload, which is the main thing an agent needs here. Only the default-tab resolution and failure modes remain unstated, which are secondary for a three-optional-parameter read tool.

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 100%, so all three parameters are already documented, including the token-saving default of 3000 characters. The description's phrase "token-dense compact DOM" reinforces the token-economy rationale but adds no syntax or format detail beyond the schema.

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 ("Extracts") and enumerates the exact artifacts returned: page title, URL, compact DOM, indexed interactive elements with refs, and clean text. An agent can distinguish this read/inspection tool from siblings like browser_screenshot or browser_evaluate, though no sibling is named explicitly.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, and no mention of the natural pairing with browser_click via the returned refs. The agent must infer that this is the discovery step before interaction.

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

Deploy Server

Other Tools