Skip to main content
Glama
Silbercue

Public Browser

by Silbercue
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

capture_image

Capture a pixel-level WebP screenshot to inspect canvas or chart rendering, verify animations, or fulfill explicit screenshot requests. Use for visual checks where DOM text extraction is unnecessary.

Instructions

Pixel-level screenshot (WebP, max 800px, <100KB). Only for canvas or chart content without DOM text, pixel-level rendering or animation checks, or when the user explicitly asks for a screenshot. Returns no refs and reads no text — that is view_page.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
somNoOverlay numbered labels matching view_page refs (Set-of-Mark)
full_pageNoCapture the full scrollable page, not just the viewport

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.10.5
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedInput schema / properties / full_page / description
      Previous value: -"Capture full scrollable page instead of just viewport"New value: +"Capture the full scrollable page, not just the viewport"
    • changedInput schema / properties / som / description
      Previous value: -"Overlay numbered labels on interactive elements matching view_page ref IDs (Set-of-Mark)"New value: +"Overlay numbered labels matching view_page refs (Set-of-Mark)"
  2. First observedv2.7.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries full behavioral disclosure. It states that the tool returns no refs and reads no text, and gives output constraints (WebP, 800px, <100KB). It does not explicitly say 'does not modify the page' but that is strongly implied by the screenshot nature; the disclosed constraints are sufficient for an agent to set expectations.

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?

The description is two sentences, front-loaded with the core definition and constraints, followed by usage guidance and sibling differentiation. Every word earns its place; no redundancy or fluff.

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 simple tool with two optional boolean parameters and no output schema, the description covers purpose, constraints, use cases, and key behavioral differences from view_page. A minor gap is that it doesn't explicitly describe the returned image data format, but the WebP and size details imply the output adequately.

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%: both 'som' and 'full_page' have clear descriptions in the schema. The tool description does not add extra parameter-level detail, but since the schema already documents both parameters adequately, the baseline score of 3 is appropriate.

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?

The description opens with a precise definition: 'Pixel-level screenshot' with concrete format and size constraints (WebP, max 800px, <100KB). It further distinguishes itself from view_page by stating that it returns no refs and reads no text, making the tool's purpose unambiguous and clearly separated from its sibling.

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

Usage Guidelines5/5

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

Usage is explicitly scoped: 'Only for canvas or chart content without DOM text, pixel-level rendering or animation checks, or when the user explicitly asks for a screenshot.' It also names the alternative (view_page) for cases involving refs/text, giving the agent clear routing guidance.

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