Skip to main content
Glama
Brave Session MCP

Brave Session MCP

by MacStenk

brave_screenshot

Read-only

Captures a screenshot of a specified tab in CSS pixel resolution to reduce image tokens on Retina displays, with optional width resizing.

Instructions

Zeigt einen Screenshot des angegebenen Tabs in CSS-Pixelauflösung statt Geräteauflösung (auf Retina-Displays deutlich weniger Bild-Tokens). Bild-Tokens richten sich nach Pixelabmessungen, nicht nach Dateigröße.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tabId": "<tabId>"
    },
    "name": "brave_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
tabIdYesStabile Tab-ID aus brave_tabs.
widthNoZielbreite in Pixeln (320–1280); verkleinert das Bild als JPEG weiter. 320–512 erreicht das Token-Niveau von OpenAIs detail:low. Weglassen: volle CSS-Breite als PNG.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), and the description adds genuinely new behavioral context: output is rendered at CSS pixel resolution, which yields far fewer image tokens on Retina displays, and tokens scale with pixel dimensions rather than file size. It does not cover failure behavior (e.g., invalid or closed tabId), so it stops short of a 5.

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?

Two compact sentences with the core behavior and the token-saving consequence front-loaded. The second sentence slightly restates the token point made in the parenthetical, but nothing is padded or off-topic.

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 two-parameter read-only capture tool with full schema coverage and no output schema, the description supplies the essential behavioral framing (resolution mode, token cost). Only edge cases such as missing/invalid tabs are unaddressed, a minor gap given the annotations.

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 description coverage is 100%, so both tabId and the width range/JPEG trade-off are already fully documented in the schema. The description adds no parameter-level detail beyond that, so the baseline of 3 applies.

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 ('Zeigt einen Screenshot des angegebenen Tabs') and clarifies the rendering mode (CSS pixel vs. device resolution), which is the key distinguishing behavior. It does not name any sibling tool, but no sibling appears to compete for the same screenshot job, so differentiation is implicit rather than explicit.

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?

The token-efficiency rationale implies why an agent would pick this over a device-resolution capture, but there is no explicit when-to-use / when-not-to-use statement or named alternative. Usage is left to inference from the Retina/token explanation.

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