Skip to main content
Glama
Sign In

Refs

by video.refs
OverviewDiscussionsAdmin

See a video frame by frame

get_frames
Read-only

One video's labelled frame sheets as images, so you can see the reference instead of guessing from text: the hook (first 3 s at 0.25 s steps), one frame per shot, and the whole film at fixed steps where measured. sheet "transitions" adds every frame around each cut and in-shot change, for timing transitions to the frame. Each image follows a caption saying how its labels read. Accepts the same ids as get_blueprint. Needs a Refs account with Pro; without one, the app asks the user to sign in. search_videos is free.

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": {
      "id": "<id>"
    },
    "name": "get_frames"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesREF-0005, a refs.video/v/… link, a YouTube/X link, an id from search_videos, or one of your brand films (brand:<import>:<film>)
sheetNoDefault all (hook, shots and timeline; ask for "transitions" separately)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / context
      Removed value: -{
-  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
-  "type": "string"
-}
    • removedInput schema / properties / llm_model
      Removed value: -{
-  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "id",
-  "context",
-  "llm_model"
-]New value: +[
+  "id"
+]
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the readOnly/non-destructive annotations, the description discloses an auth requirement (Refs account with Pro, sign-in prompt otherwise) and a cost distinction (search_videos is free), which are real gating behaviors. It also describes the response shape qualitatively (images each followed by a caption explaining labels), though image counts or size limits are unstated.

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 key concept (frame sheets as images) is front-loaded and every sentence carries content about sheets, labels, ids, or access. The dense clause stacking and phrase 'where measured' make it slightly harder to parse than ideal.

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 output schema, the description steps in to describe returns (captioned images), and it covers access prerequisites, id compatibility, and per-sheet content. Missing only operational details such as how many images to expect or whether large requests are truncated.

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 already 100%, so the baseline is 3, but the description adds substantial meaning the schema lacks: what 'hook' (first 3 s at 0.25 s steps), 'shots' (one frame per cut), and 'timeline' actually contain, and the important nuance that the default 'all' excludes 'transitions'. It also notes that the same ids as get_blueprint are accepted.

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 states a specific verb and resource ('One video's labelled frame sheets as images') and enumerates the sheet variants, so an agent knows exactly what it returns. It is somewhat less crisp at distinguishing itself from get_blueprint or storyboard than it could be, only linking to them via shared id format.

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?

It gives a clear condition for the 'transitions' sheet (timing transitions to the frame) and a motivation for the tool generally ('see the reference instead of guessing from text'). It does not say when to prefer get_blueprint or storyboard, nor when frame sheets are unnecessary, so the routing among siblings is only implied.

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

All Refs 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