Skip to main content
Glama
Sign In
Antigravity Browser Operator

Antigravity Browser Operator

by hashan-lakshitha
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

browser_screenshot

Captures a screenshot of the active or a specified Chrome tab and saves it to disk as PNG or JPEG, optionally overlaying numbered element badges for visual reasoning.

Instructions

Captures a visible screenshot of the active or specified tab in Chrome and saves it as an image on disk.

Input Schema

NameRequiredDescriptionDefault
tabIdNoOptional tab ID.
formatNoImage format (defaults to "jpeg" for fast lightweight transfer).
qualityNoCompression quality 1-100 (defaults to 80 for jpeg).
annotateNoWhen true, paints visual Set-of-Marks (SoM) numbered badges matching element refs directly onto the screenshot before capturing, perfect for multimodal visual reasoning.
savePathNoOptional file path to save the image. If omitted, saves to project screenshots folder.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.4.0
    • addedInput schema / properties / annotate
      Added value: +{
+  "description": "When true, paints visual Set-of-Marks (SoM) numbered badges matching element refs directly onto the screenshot before capturing, perfect for multimodal visual reasoning.",
+  "type": "boolean"
+}
    • addedInput schema / properties / format
      Added value: +{
+  "description": "Image format (defaults to \"jpeg\" for fast lightweight transfer).",
+  "enum": [
+    "jpeg",
+    "png"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / quality
      Added value: +{
+  "description": "Compression quality 1-100 (defaults to 80 for jpeg).",
+  "type": "number"
+}
    • addedInput schema / properties / savePath
      Added value: +{
+  "description": "Optional file path to save the image. If omitted, saves to project screenshots folder.",
+  "type": "string"
+}
  2. First observedv1.0.1

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two useful traits: the capture is 'visible' (viewport-limited, not full-page) and it writes a file to disk. It omits what is returned (file path vs. image payload), overwrite behavior on savePath collisions, and failure modes for an invalid tabId.

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?

A single front-loaded sentence that identifies the action, target, and persistence behavior with no filler. Nothing in it is redundant or out of order.

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

Completeness3/5

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

Five all-optional parameters and no output schema mean the description should clarify what the caller gets back and whether the write is safe to repeat; neither is addressed. The stated purpose and disk-write disclosure make it viable, but not complete for a tool that mutates the filesystem.

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 description coverage is 100%, so all five parameters including format, quality, annotate, and savePath defaults are already documented in the schema. The only added meaning is the 'active or specified tab' phrasing, which implicitly explains what happens when tabId is omitted; that is a marginal contribution over structured data.

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 names a specific verb (captures) and resource (screenshot of a tab in Chrome), plus scope ('active or specified tab') and the side effect (saves as an image on disk). It does not explicitly contrast with any sibling, but no sibling overlaps in function, so an agent can place it accurately.

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?

The description states what it does but never says when to reach for it versus alternatives such as browser_get_dom or browser_evaluate for page inspection, nor any conditions or exclusions. The only implied usage cue is 'active or specified tab', which is about targeting, not tool selection.

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