Skip to main content
Glama

obsbot_capture_snapshot

Captures a single still frame from the OBSBOT camera as an image for framing, lighting, and exposure checks, with adjustable resolution, quality, and source (device, virtual, or NDI).

Instructions

Grab one still frame from the camera and return it as an image (for you to see and for framing/lighting/exposure checks). resolution is the longest edge in pixels, 256-1920, default 640 — larger images cost proportionally more tokens, so ask for more only when you need the detail. NOTE: before calling, ensure the camera is focused (call obsbot_focus_auto for autofocus) unless otherwise directed. source: device (default) | virtual | ndi. If the camera is in use by another app, returns a message instead of an image.

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": "obsbot_capture_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
cameraNo
sourceNodevice
qualityNo
settleMsNo
resolutionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changedv0.9.6
    • removedInput schema / properties / quality / allOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "maximum": 100,
      -    "minimum": 1,
      -    "type": "number"
      -  }
      -]
    • addedInput schema / properties / quality / maximum
      Added value: +100
    • addedInput schema / properties / quality / minimum
      Added value: +1
    • addedInput schema / properties / quality / type
      Added value: +"number"
    • removedInput schema / properties / resolution / allOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "maximum": 1920,
      -    "minimum": 256,
      -    "type": "number"
      -  }
      -]
    • addedInput schema / properties / resolution / maximum
      Added value: +1920
    • addedInput schema / properties / resolution / minimum
      Added value: +256
    • addedInput schema / properties / resolution / type
      Added value: +"number"
    • removedInput schema / properties / settleMs / allOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "maximum": 15000,
      -    "minimum": 0,
      -    "type": "number"
      -  }
      -]
    • addedInput schema / properties / settleMs / maximum
      Added value: +15000
    • addedInput schema / properties / settleMs / minimum
      Added value: +0
    • addedInput schema / properties / settleMs / type
      Added value: +"number"
  2. Addedv0.6.2

TDQS

A3.9/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it discloses non-obvious behaviors: the return is an image the agent can see, larger resolutions cost proportionally more tokens, and if the camera is busy with another app it returns a message instead of an image. It does not explain what settleMs or quality do behaviorally (e.g., latency vs. compression tradeoffs), which leaves part of the runtime profile opaque.

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-loads the core action, then prerequisites, then the source enum, then the failure mode — a sensible ordering. The middle sentence packs range, default, and cost rationale into one long clause, but no sentence is expendable.

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?

With no annotations and no output schema, the description does the needed work: it explains the return value shape and the degraded 'message instead of image' case, and gives a focus prerequisite. The main remaining gap is that three parameters (camera, quality, settleMs) are undocumented anywhere, which for a 5-parameter tool is a real omission but not a fatal one since all are optional with defaults.

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%, so the description must compensate, and it only covers two of five parameters: resolution (range 256-1920, default 640, plus the token-cost implication) and source (device|virtual|ndi with default). camera, quality, and settleMs are left entirely to bare numeric/string types in the schema — notably settleMs, whose purpose an agent cannot infer from the name alone.

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+resource+return: 'Grab one still frame from the camera and return it as an image.' That distinguishes it from recording/preview siblings by outcome, but it never names or contrasts with the other snapshot tools in the family (obsbot_tail2_snapshot, obsbot_tail2_capture_photo), so an agent facing several capture options gets no explicit tie-breaker.

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 real usage context — 'for framing/lighting/exposure checks' — plus a concrete prerequisite ('ensure the camera is focused (call obsbot_focus_auto) unless otherwise directed') and a sizing rule ('ask for more only when you need the detail'). No when-not-to-use guidance relative to the sibling capture/record tools, which keeps it out of 5 territory.

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