Skip to main content
Glama

Grab a frame

grab_frame

Extract a frame from a local video at a specified timestamp and return it as a viewable image; optionally save the full-resolution frame as JPG, PNG, or WebP for inspection or export.

Instructions

Return the frame at a timestamp as an image you can look at (e.g. 'what's on screen at 1:23?', 'is the logo legible here?'). Optionally also save it at full resolution as JPG, PNG or WebP.

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": {
      "path": "<path>"
    },
    "name": "grab_frame"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoTime: seconds, "MM:SS", "HH:MM:SS.mmm" or "50%".50%
pathYesAbsolute path to a local video file. ~ is expanded.
formatNojpeg
max_widthNoWidth of the returned preview image.
overwriteNo
save_pathNoAlso save the frame at full resolution here (.jpg, .png or .webp).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations mark it readOnlyHint=false yet destructiveHint=false, which is puzzling until the description explains the write: it can optionally save a full-resolution file. That is genuine added context beyond the annotations, and the format list (JPG, PNG, WebP) helps. However, nothing is said about overwrite behavior, whether an existing file is replaced, or where the preview lives — notable gaps for a tool flagged as non-read-only.

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?

Two sentences, front-loaded with the primary return behavior and followed by the optional side effect. The parenthetical examples earn their place by conveying intent, and there is no filler.

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 six parameters, no output schema, and moderate schema coverage, the description does enough: it tells the agent what comes back (an image), what the optional save does, and how to express a timestamp. Remaining gaps are the undocumented overwrite/max_width semantics rather than the core contract.

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 67%, and the description reinforces the timestamp and save concepts while adding the useful distinction that the returned image is a preview versus the full-resolution saved copy. It still leaves overwrite and max_width unaddressed, and the 'JPG, PNG or WebP' list only partially maps to the schema's jpeg/png format enum with no explanation of how save_path extension interacts with format.

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 (return) and resource (the frame at a timestamp) and clarifies the output form: an image the agent can visually inspect. The examples ('what's on screen at 1:23?') signal a vision/single-frame use case that reads differently from bulk siblings like extract_frames or sample_frames, though no sibling is named explicitly.

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?

The two example phrasings give concrete situational triggers for when to reach for this tool (inspecting a specific moment, checking legibility). There is no explicit when-not guidance or named alternative for range/bulk extraction, so it stops short of a 5.

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