Skip to main content
Glama

Look at frames

get_screenshot
Read-onlyIdempotent

Up to 6 moments, or one filmstrip (from, to, every). Look before a change and after. Cost: Free.

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": "get_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoUp to 6 film seconds to draw.
toNoA filmstrip: the last second.
fromNoA filmstrip: the first second of the range.
sizeNoLong side in pixels; 768 when left out.
everyNoFilmstrip: seconds between frames (down to 1/60), at most 24.
video_idNoVideo; the open one if left out.
output_idNoOutput id.
base_versionNoVersion id.

Output Schema

NameRequiredDescriptionDefault
codeNo
costNo
errorNo
stateNo
statusNo
dry_runNo
messageNo
plan_idNo
style_idNo
video_idNo
availableNo
import_idNo
output_idNo
studio_urlNo
version_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / every / description
      Previous value: -"A filmstrip: seconds between frames (down to 1/60 to see a move frame by frame), at most 24 frames."New value: +"Filmstrip: seconds between frames (down to 1/60), at most 24."
    • changedInput schema / properties / video_id / description
      Previous value: -"The video; the open one when left out."New value: +"Video; the open one if left out."
  2. Changed2 schema fields changed
    • changedInput schema / properties / every / description
      Previous value: -"A filmstrip: seconds between frames, at most 24 frames."New value: +"A filmstrip: seconds between frames (down to 1/60 to see a move frame by frame), at most 24 frames."
    • changedInput schema / properties / every / minimum
      Previous value: -0.1New value: +0.016666666666666666
  3. Changed7 schema fields changed
    • changedInput schema / properties / base_version / description
      Previous value: -"A version_id to read; the live version when left out."New value: +"Version id."
    • addedInput schema / properties / every
      Added value: +{
      +  "description": "A filmstrip: seconds between frames, at most 24 frames.",
      +  "maximum": 60,
      +  "minimum": 0.1,
      +  "type": "number"
      +}
    • addedInput schema / properties / from
      Added value: +{
      +  "description": "A filmstrip: the first second of the range.",
      +  "maximum": 36000,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • changedInput schema / properties / output_id / description
      Previous value: -"An output (Short, hook, shape); the main video when left out."New value: +"Output id."
    • addedInput schema / properties / to
      Added value: +{
      +  "description": "A filmstrip: the last second.",
      +  "maximum": 36000,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • changedInput schema / properties / video_id / description
      Previous value: -"The video, from list_videos."New value: +"The video; the open one when left out."
    • changedInput schema / required
      Previous value: -[
      -  "video_id",
      -  "at"
      -]New value: +[]
  4. Changed2 schema fields changed
    • changedInput schema / properties / output_id / description
      Previous value: -"A Short, hook or shape of the video; the main video when left out."New value: +"An output (Short, hook, shape); the main video when left out."
    • changedInput schema / properties / size / description
      Previous value: -"The long side in pixels, 256 to 1280; 768 when left out."New value: +"Long side in pixels; 768 when left out."
  5. Added

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds 'Cost: Free' and the frame-count/range limits, which are genuine behavioral facts not in annotations, but it says nothing about failure modes (e.g., no open video) or how frames are returned beyond what the output schema covers.

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, front-loaded fragments with no filler; the mode constraint, workflow hint, and cost all land immediately. It is slightly over-compressed, since terms like 'moments' and 'filmstrip' are used before being defined anywhere in prose.

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 a full output schema, complete annotation coverage, and no required parameters, the tool needs little prose and the description covers modes and cost. The main remaining gap is the lack of any guidance on how this differs from other visual-inspection siblings, which matters given 46 sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description adds the crucial coupling semantics: 'at' is one mode (up to 6 moments) and 'from'/'to'/'every' form the other mutually exclusive filmstrip mode. That relationship is not stated as a whole in the per-parameter schema text, so it meaningfully informs parameter selection.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The title 'Look at frames' plus 'Up to 6 moments, or one filmstrip' conveys that the tool renders visual frames from a video, but it never uses a concrete verb+resource phrasing like 'capture screenshots of video frames'. The idiosyncratic terms 'moments' and 'filmstrip' require the schema to decode, so an agent can infer intent but not state it crisply.

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?

'Look before a change and after' implies a verification workflow, which is real usage guidance. However, it names no alternatives — nothing distinguishes it from siblings like check_video, measure_motion, or get_timeline — and gives no explicit when-not conditions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources