Skip to main content
Glama
Sign In

CueFrame

by ai.cueframe
OverviewDiscussionsAdmin

Get Media Facts

get_media_facts
Read-onlyIdempotent

Read prepared subject tracks and behind-subject mattes for one media item. For an exact readiness check, pass kind + startSec + endSec together using the same SOURCE window sent to prepare_media; exact.state is pending | ready | failed | available | unavailable. If subjectTrack was prepared without intent, omit all three filters and check the whole-source subjectTrack in facts instead. Wait for the required fact to be ready before preview_frame / score_composition.

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": {
      "mediaItemId": "<mediaItemId>"
    },
    "name": "get_media_facts"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoResolve one exact editor prerequisite. Requires startSec and endSec; the response includes the server-selected `exact` result.
endSecNoSource-out of the clip's trim, in seconds. Must be sent WITH startSec.
startSecNoSource-in of the clip's trim, in seconds. Must be sent WITH endSec — one without the other is a 400, never a silent whole-source default.
mediaItemIdYesmediaItemId (path).

Output Schema

NameRequiredDescriptionDefault
exactNoThe server-selected fact or offer for one exact source window. Present when kind, startSec, and endSec are supplied; clients consume this instead of recreating the fact hash.
factsNo
offersNoWhat is NOT yet present and could be bought. A `matte` offer appears ONLY when the request carried `startSec`+`endSec` (the clip's SOURCE window) — a matte's price is a function of its duration, so there is no honest whole-source matte quote. `transcript` is never offered: it is produced by the ingest pipeline, not bought here.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent safety, and the description layers on non-obvious behavior: the readiness state machine (pending | ready | failed | available | unavailable) and the 400-on-partial-window rule from the schema. Those are operational traits an agent cannot infer from annotations alone.

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?

Front-loaded with purpose, then two conditional usage paths, then the sequencing gate — no wasted sentences. Slightly dense with jargon (SOURCE window, exact.state, facts) that assumes familiarity with the sibling tooling.

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?

A read tool with an output schema and full annotation coverage, so return shape needn't be explained. The description still supplies the pieces an agent needs to call it correctly: mode selection, the state enum, and the downstream ordering constraint.

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 cross-parameter semantics the schema does not: the three filters are a coupled unit tied to the prepare_media SOURCE window, and omitting all three yields a whole-source check on facts.subjectTrack. It stops short of describing units or edge cases for individual params, which the schema already handles.

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?

States a specific verb and resource: 'Read prepared subject tracks and behind-subject mattes for one media item.' It is clearly distinguishable from prepare_media (which creates the artifacts) and preview_frame / score_composition (which consume them), both 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 Guidelines5/5

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

Gives explicit routing rules: pass kind + startSec + endSec together using the same SOURCE window sent to prepare_media for an exact check; omit all three filters if the track was prepared without intent. It also states the sequencing precondition — wait for the fact to be ready before preview_frame / score_composition.

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

All CueFrame 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