Skip to main content
Glama
Sign In
Chrome Bridge

Chrome Bridge

by frsorrentino
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

screenshot

Read-onlyIdempotent

Capture the visible Chrome viewport as PNG at the current scroll position or for mobile, tablet, and desktop presets, optionally saving to a file.

Instructions

Screenshot of the visible viewport only (PNG), at the current scroll position, or one per viewport preset with presets. Read-only. Activates the tab in the background without stealing window focus, then restores the previous tab. Downscaled to ≤1568px: for fine print, element_screenshot with scale.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
tab_idNoTarget tab; omitted = last tab navigated in this session, else the active one
presetsNoResizes the window per preset, then restores it; not phone emulation. A refused width is reported, not shot. save_to = directory
save_toNoAbsolute path: write the PNG there and return the path instead of the content
if_changedNoSame pixels as the last screenshot of this tab: a note instead of the image. false = always send it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.28.0
    • addedInput schema / properties / if_changed
      Added value: +{
+  "default": true,
+  "description": "Same pixels as the last screenshot of this tab: a note instead of the image. false = always send it",
+  "type": "boolean"
+}
    • changedInput schema / properties / presets / description
      Previous value: -"One capture per preset, window restored; save_to = directory, one file each"New value: +"Resizes the window per preset, then restores it; not phone emulation. A refused width is reported, not shot. save_to = directory"
  2. Changed1 schema field changedv1.16.1
    • addedInput schema / properties / presets
      Added value: +{
+  "description": "One capture per preset, window restored; save_to = directory, one file each",
+  "items": {
+    "enum": [
+      "mobile",
+      "tablet",
+      "desktop"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
  3. Changed1 schema field changedv1.11.0
    • addedInput schema / properties / save_to
      Added value: +{
+  "description": "Absolute path: write the PNG there and return the path instead of the content",
+  "type": "string"
+}
  4. Changed1 schema field changedv1.10.0
    • addedInput schema / properties / tab_id / description
      Added value: +"Target tab; omitted = last tab navigated in this session, else the active one"
  5. First observedv1.8.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover the read-only/idempotent safety profile, but the description adds non-obvious behavior: background tab activation without stealing window focus, restoring the previous tab, and downscaling to ≤1568px. These are exactly the operational traits an agent could not infer from structured fields.

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?

Three dense sentences, all front-loaded and purposeful. The scope, behavior, and alternative are ordered by importance with zero filler.

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?

Covers output format (PNG), the save_to-vs-inline-content alternative, and the if_changed note, so even without an output schema an agent knows what to expect back.

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 four parameters are already documented. The description reinforces preset semantics ('resizes the window per preset... not phone emulation'), which adds slight clarity, but the heavy lifting is done by the schema, so the baseline 3 applies.

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

Purpose5/5

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

States a specific verb and output (PNG screenshot) plus precise scope: 'visible viewport only... at the current scroll position'. This implicitly contrasts with full_page_screenshot and element_screenshot, letting an agent differentiate from siblings without opening schemas.

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?

Explicitly routes fine-print needs to element_screenshot with scale, and describes preset usage. It does not explicitly name full_page_screenshot as the alternative for whole-page capture, leaving that to inference from 'viewport only'.

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