Skip to main content
Glama

screenshot

Read-only

Capture the current screen as an image to visually verify UI appearance—colors, contrast, stacking—that a UI tree cannot show, and to read tap/drag coordinates on mobile devices.

Instructions

Capture a screenshot of the current screen. Use it to check how something LOOKS — the UI tree carries no colour, contrast, or stacking information, so a screen can pass every check the tree can express and still be visibly broken. Saved to disk; over MCP, pass inline: true to receive the image itself. On a phone or tablet its pixels are the coordinates tap/drag take, so a point read off it can be tapped as is.

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
outNoFile path to write the PNG to on the machine running this server (default: a temp file).
inlineNoReturn the image itself so you can see it, not just the file path. Set this to true whenever you need to judge how the screen LOOKS, or whenever you cannot open files on the machine running this server — otherwise the screenshot is only written to disk and you never see it. It costs context, so skip it when you only need to confirm an action happened (the response already tells you what changed). The image has the same size as the screenshot (a JPEG when the PNG is large), so a point read off it is the coordinate tap and drag take.
session_idNoSession ID to target. Optional: falls back to the MCP-server-held dev_start session, then this project's `vibeview dev --detach` state, if either is available.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Consistent with readOnlyHint=true, and it goes well beyond it: default behaviour is a disk write, inline=true returns the image, images may be transcoded to JPEG when the PNG is large, and inline costs context. It does not cover auth/permissions, but for a read-only capture tool that is a minor omission.

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?

Front-loaded with purpose, then the LOOKS rationale, then the inline decision, then the coordinate payoff — a sensible ordering with no filler sentences. It is dense and em-dash-heavy, and the coordinate point is stated twice (description and inline param), which trims a point.

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?

With no output schema, the description carries the return-value burden and does so: it explains that the default result is only a file path and that inline returns the image itself. Combined with the coordinate note and form-factor caveat, nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: the pixel-to-coordinate relationship with tap/drag on phone and tablet form factors, and the practical rule for choosing inline. The out-path semantics are left entirely to the schema, which is acceptable given its detail.

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?

Names a specific verb and resource ('Capture a screenshot of the current screen') and immediately distinguishes it from the tree-based inspection path, which is the main sibling ambiguity in this catalog. An agent knows exactly what it gets and why it differs from find/alert-style checks.

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?

Gives an explicit when: checking how something LOOKS, with the reason (the UI tree carries no colour, contrast, or stacking information) and the failure mode it catches. It also gives an explicit when-not for the inline flag — skip it when you only need to confirm an action happened — which is the key decision an agent faces here.

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