Skip to main content
Glama
Sign In
umbra

umbra

by lxchx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Screenshot

screenshot

Captures a browser tab as JPEG base64 for vision-language model reasoning, with full-page and quality options.

Instructions

JPEG → base64 (q=65 cheap). For VLM visual reasoning. For text use extract_markdown.

Ex: screenshot('t0', full_page=True) → {"b64":"...","fmt":"jpeg","len":48201}

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>"
    },
    "name": "screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
tab_idYes
qualityNo
full_pageNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations, so the description carries the burden. It does disclose cost cues (q=65 cheap) and the response shape via the example, but says nothing about viewport vs full-page behavior, whether it scrolls or waits for load, or failure modes on detached tabs.

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 lines, cost and use case front-loaded, no filler. The telegraphic style ('JPEG → base64 (q=65 cheap)') borders on cryptic but each element carries 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?

An output schema exists, so return values need not be restated. However, for a 3-param tool with zero schema descriptions, the missing definition of tab_id and the unspecified scope of full_page leave real gaps for correct invocation.

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 0%, so the description must compensate. It explains quality indirectly ('q=65 cheap') and full_page via the example call, but tab_id — the only required parameter — is never defined, leaving the agent to infer it comes from list_tabs.

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 the output format precisely (JPEG → base64) and the intended consumer (VLM visual reasoning), and explicitly redirects text needs to extract_markdown. It never states the verb 'capture a page' or the target (tab_id), so the purpose is inferred partly from the name and example.

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?

'For VLM visual reasoning. For text use extract_markdown' gives a clear use condition plus the named alternative sibling. It omits the other visual sibling screenshot_region and any precondition (e.g., page loaded) for choosing this tool.

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