Skip to main content
Glama
Sign In
umbra

umbra

by lxchx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Screenshot Region

screenshot_region

Captures a JPEG image of a specified rectangular area on a browser tab, enabling isolated captcha tiles or crops for visual model inspection.

Instructions

JPEG of a (x,y,w,h) region. For captcha tiles, isolated VLM crops. Rect from inspect_element.

Ex: screenshot_region('t0', 100, 200, 300, 100) → {"b64":"...","fmt":"jpeg","rect":{x,y,w,h}}

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": {
      "tab_id": "<tab_id>",
      "x": "<x>",
      "y": "<y>",
      "w": "<w>",
      "h": "<h>"
    },
    "name": "screenshot_region"
  }
}

Input Schema

NameRequiredDescriptionDefault
hYes
wYes
xYes
yYes
tab_idYes
qualityNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are supplied, so the description must carry behavioral weight. It discloses the output form (base64 JPEG with a rect echo), which is genuinely useful, but never states that this is a pure read with no page mutation, nor anything about cost or the quality knob's effect.

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?

Three short fragments plus a worked example — front-loaded and waste-free. The telegraphic style ('isolated VLM crops') is efficient but slightly cryptic for an agent unfamiliar with the jargon.

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?

An output schema exists, so the return shape needn't be spelled out, and the description does hint at it anyway. What's missing for correct invocation is the units/coordinate space for x/y/w/h and any guidance on the undocumented 'quality' parameter, leaving a real gap at 0% schema coverage.

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 0% across 6 parameters, so the description is the only source of meaning. The example maps tab_id and x/y/w/h positionally and hints that the rect comes from inspect_element, but units (pixels? CSS px?) are unstated and the optional 'quality' parameter is never mentioned at all.

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?

States a specific verb and resource: a JPEG capture of an (x,y,w,h) region on a given tab, which cleanly separates it from the sibling 'screenshot' (full viewport). The example call makes the operation unambiguous.

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

Usage Guidelines4/5

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

Gives concrete use contexts — captcha tiles and isolated VLM crops — and tells the agent where rect values come from ('Rect from inspect_element'), which is essentially a workflow instruction. It stops short of naming when to pick 'screenshot' instead, so no explicit alternative routing.

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