Skip to main content
Glama

Capture Web Screenshot

capture_web_screenshot
Idempotent

Capture the current visible viewport of a configured browser page as an inline, content-addressed PNG artifact without scrolling, navigating, or running page JavaScript.

Instructions

Capture the current visible viewport of one configured page as an inline, content-addressed PNG artifact. The operation never scrolls, navigates, or evaluates page JavaScript.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "target_id": "TARGET_ID_FROM_LIST_BROWSER_TARGETS",
      "cdp_endpoint": "http://127.0.0.1:9222"
    },
    "name": "capture_web_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
target_idYesExact CDP target identifier selected from the endpoint's target listing.
cdp_endpointYesLiteral loopback Chrome DevTools Protocol endpoint.
allowed_originsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true, but the description adds real behavioral substance beyond them: it will not scroll, navigate, or evaluate JavaScript, so the agent knows the returned image is the untouched viewport. It also discloses the artifact encoding (inline, content-addressed PNG). It stops short of describing failure modes or whether an existing page session is required.

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?

Two sentences, no filler, and the core purpose is front-loaded before the constraint clause. Every sentence carries information an agent needs.

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 three-parameter capture tool with no output schema, the description covers purpose, scope, side-effect boundaries, and return form well. The remaining gap is the unlabeled allowed_origins parameter and the absence of any note on target availability or error behavior, but these are modest for a tool of this simplicity.

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 67%, so two of the three parameters are already documented (target_id, cdp_endpoint) and the description repeats none of that. The undocumented parameter, allowed_origins, is left entirely to its self-descriptive name with no explanation of origin allowlisting in either the schema or the description, which is the one place added prose would have helped. Baseline 3 is appropriate at this coverage level.

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 (Capture), a precise scope (current visible viewport of one configured page), and the output form (inline, content-addressed PNG artifact). It doesn't explicitly distinguish itself from siblings like compare_web_screenshots or capture_browser_scenario, but the 'one configured page' phrasing narrows it enough for an agent to tell what it produces.

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 only implied: the agent can infer 'use this to get a PNG of the current viewport', and the exclusion clause tells it the tool will not scroll, navigate, or run JS, which shapes expectations. There is no statement of when to prefer this over a scenario capture or a screenshot comparison tool, and no prerequisites such as needing a live CDP target.

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