Skip to main content
Glama

describe_frame

Capture the current video frame as a downscaled image, optionally seeking to a specific position first, so you can inspect what is on screen.

Instructions

Return the frame showing right now as an image, so you can see what is on screen. Optionally seek to a position first. The picture is the one the viewer is watching — GUI, CLI and MCP share a single player. Downscaled to keep the response small; subtitles and on-screen controls are not burned in.

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": "describe_frame"
  }
}

Input Schema

NameRequiredDescriptionDefault
max_edgeNoLongest edge in pixels (64-2048, default 768)
positionNoSeek here (seconds) before capturing

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description does most of the work: it states the output is an image, that it is downscaled for size, and that subtitles/controls are not burned in. 'GUI, CLI and MCP share a single player' usefully warns that the capture reflects a shared playback state other clients can change. It does not say whether using position moves playback persistently, which a mutation-adjacent tool should mention.

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?

The description is short, front-loaded with the core action, and each sentence carries information. The clause about the shared player is slightly tangential but justified because it explains why the frame may not match the caller's expectation.

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?

There is no output schema, so the description must explain the return value, and it does: an image, downscaled, without burned-in subtitles or controls. For a two-optional-parameter capture tool this is nearly complete; the only gap is whether the optional seek changes playback position after the capture.

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 100%, so both parameters are already documented and the description only restates that seeking happens before capture. The note about downscaling adds a little context for max_edge, but there is no added detail on valid values or the seek's effect on playback state.

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?

The description gives a specific verb and resource: return the current frame as an image. 'The frame showing right now' and 'the picture the viewer is watching' set it apart from step/seek-style siblings by scoping it to the live on-screen frame, though it never names an alternative tool.

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 sentence 'Optionally seek to a position first' tells the agent one way to use the tool, but says nothing about when to choose this over seek or frame_step, or when to prefer a contact sheet. The guidance is implied rather than stated, so an agent must infer the trade-offs.

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