Skip to main content
Glama

screenshot

Capture an agent tab, including embedded frames, even when the browser window is hidden. Set full-page mode to record the entire page up to 6000px.

Instructions

Screenshot an agent tab, including embedded frames. Works when the window is hidden.

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
tabIdNoAgent tab id from tabs_list. Omit to use the last agent tab.
fullPageNoCapture the whole page, not just the visible part (max 6000px tall). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.4

TDQS

A3.6/5.0
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 contribute two genuine behavioral facts: frames are captured and hidden windows still work. It omits what the call returns, whether it blocks on slow pages, and any auth or rate-limit behavior, so the mutation-free read profile must be guessed from the verb alone.

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 short sentences, zero filler, with the core action front-loaded before the caveat. Nothing is repeated from the schema and no sentence could be removed without losing information.

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?

For a two-parameter, zero-required tool with no output schema and no annotations, the description is decent but incomplete: it never characterizes the return value (image bytes, URL, saved file) or any size/format behavior beyond the schema's 6000px note. An agent knows what it does and one key capability, but not what it gets back.

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 description coverage is 100%, so the baseline is 3; the description adds the fullPage-relevant framing of what a capture contains (embedded frames) and the hidden-window capability that affects expectations for the tabId parameter. It adds no per-parameter detail beyond what the schema already documents, which is acceptable at full coverage.

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?

States a specific verb and resource ('Screenshot an agent tab') plus a scope qualifier ('including embedded frames'), which is concrete enough for an agent to know what it produces. It stops short of distinguishing itself from content-reading siblings like page_text or page_elements, and never says whether the output is image data or a file path.

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 by the verb: an agent can infer 'use this when you need a visual capture rather than text.' There is no explicit when-to-use versus page_text/page_elements, and no stated prerequisites; the 'works when the window is hidden' line is a capability note, not routing guidance.

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