Skip to main content
Glama

Treza

by io.github.treza-labs
OverviewDiscussionsAdmin

Make video

make_video

The quickest way to make a video from a description: no template, node types or graph to wire. Picks a video model that renders the shape and length asked for (Veo 3.1 Lite unless a model is named or it cannot), prepares the render, and answers like estimate_run_cost: the price, whether the balance covers it, and a quoteId. It does NOT start the render: tell the person what it makes and the price, and once they accept, call run_pipeline with the returned pipelineId and quoteId (no inputs; the prompt is saved). Clients that show panels put the price in front of them with a Start render button. Use 9:16 for Shorts, Reels and TikTok. With maxPriceUsd, a video over it is refused with its price rather than shortened. To extend or continue a video the account already has ("continue it", "make it longer", "the next scene", "what happens next"), pass its url as continueFromVideoUrl: the new clip opens on that video's exact last frame and keeps its shape, and prompt says only what happens next. Never answer one of those with a fresh clip from the prompt alone, which is a different shot that cannot be cut onto the end. For anything beyond one generated clip (clipping a long video, music, narration, editing a file) use a template, assemble_video or edit_asset instead. Needs the pipelines:write scope; the run needs pipelines:run.

Input Schema

NameRequiredDescriptionDefault
nameNoWhat to call the render.
modelNoA video model id from get_node_type video-gen, only when the person asked for a specific model.
promptYesWhat the video shows, in the person's words or a fuller description of them.
withAudioNoGenerate sound with the video where the model can. Defaults to true.
aspectRatioNo"9:16" vertical (Shorts, Reels, TikTok), "16:9" horizontal (the default), "1:1" square.
durationSecNoLength in seconds. A model that renders fixed takes uses the next one up (at most 2s longer), and says so. Defaults to 4.
maxPriceUsdNoThe most the person will pay for this render, if they said.
continueFromVideoUrlNoThe url of a video in the account's library (from list_assets or a run's outputs), copied exactly, to continue. Its last frame becomes this clip's first frame. Pass that video's aspectRatio too.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / continueFromVideoUrl
      Added value: +{
+  "description": "The url of a video in the account's library (from list_assets or a run's outputs), copied exactly, to continue. Its last frame becomes this clip's first frame. Pass that video's aspectRatio too.",
+  "minLength": 1,
+  "type": "string"
+}
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover the safety profile; the description adds the critical behavior that this tool does not start the render and returns price/balance/quoteId/pipelineId. It also discloses model selection fallback (Veo 3.1 Lite), the exact refusal behavior when maxPriceUsd is exceeded, duration rounding, and required scopes (pipelines:write, pipelines:run).

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 the core promise and the quote-not-render contract; nearly every sentence carries a routing rule or a behavioral fact. It is a single dense block of ~200 words, however, and the later continuation paragraphs are harder to scan than the opening.

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?

An 8-parameter, 1-required creation tool with no output schema: the description compensates by describing the return payload and the mandatory follow-up call. Scope requirements, default model, and cost ceiling behavior are all covered, so nothing needed to invoke it correctly is missing.

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; the description earns more by giving continueFromVideoUrl the semantics the schema doesn't convey (new clip opens on the source's last frame, keeps its shape, prompt covers only what happens next). maxPriceUsd's refuse-rather-than-shorten behavior and the model default are also clarified. It stops short of adding anything for name or withAudio.

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+resource (make a video from a description) plus the defining differentiator: no template, node types or graph to wire. It names the sibling tools that cover everything else (assemble_video, edit_asset, templates), so an agent can pick between them without opening a 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?

Explicit when-to-use paths: 9:16 for Shorts/Reels/TikTok, continueFromVideoUrl for continuations, and when to fall back to templates/assemble_video/edit_asset. It also states the two-step flow (this tool quotes, run_pipeline starts) and the 'never answer a continuation with a fresh clip' exclusion, which is a real routing rule, not filler.

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

All Treza 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