Skip to main content
Glama

GetVideoFrames

by com.getvideoframes.mcp
OverviewDiscussionsAdmin

Get one frame as an image

getvideoframes_get_frame
Read-onlyIdempotent

Download one frame from a completed job and return the image bytes as MCP image content so you can see the pixels.

Use this when the user asks what a frame shows, to compare frames, or to analyze a still. Pass the job id and frame_index from getvideoframes_get_job. frame_index is frames[].index, not a position in the list.

The result content includes an image block: type "image", base64 data, and mimeType (image/jpeg, image/png, or image/webp). Read that image. A URL is not a substitute for the pixels.

getvideoframes_get_job still returns download URLs and metadata. getvideoframes_render_frames still shows the filmstrip to the user. This tool does neither of those jobs.

Input Schema

NameRequiredDescriptionDefault
idYesJob id returned by getvideoframes_create_job
sourceNojob uses the connected account. demo is the public preview. Default job
api_keyNogvf_live_ key. Omit when the MCP connection is already authorized
frame_indexYesFrame index from getvideoframes_get_job, the frames[].index field

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / source
      Added value: +{
+  "description": "job uses the connected account. demo is the public preview. Default job",
+  "enum": [
+    "job",
+    "demo"
+  ],
+  "type": "string"
+}
  2. Added

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds real context beyond that: the prerequisite of a 'completed job', the returned content shape (image block, base64, mimeType values), and the warning that a URL is not a substitute for pixels.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short paragraphs, front-loaded with the core action and return shape, then usage, then sibling disambiguation. Every sentence carries a distinct piece of information; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by describing the returned image content block and its fields, and it covers prerequisites and alternatives. An agent has everything needed to call and interpret the result.

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 is 3, but the description adds a genuinely non-obvious clarification: frame_index is 'frames[].index, not a position in the list', plus the source of the id ('from getvideoframes_get_job'). That is value beyond the schema text.

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

Purpose5/5

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

Specific verb+resource: 'Download one frame from a completed job and return the image bytes as MCP image content'. It explicitly positions itself against siblings getvideoframes_get_job (URLs/metadata) and getvideoframes_render_frames (filmstrip), so an agent can route without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States when to use it ('user asks what a frame shows, to compare frames, or to analyze a still') and names the two alternative tools with the conditions under which they, not this tool, apply. Nothing is left to inference.

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

All GetVideoFrames toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources