Skip to main content
Glama

openFlow

by io.github.molkex
OverviewDiscussionsAdmin

generate_video

Generate a video from a text prompt via Google Flow (Veo models).

video_model_key options: abra_t2v_4s (default, 7 credits), veo_3_1_t2v_lite
(10cr, visibly cleaner), veo_3_1_t2v (100cr, "Quality" tier), veo_3_1_t2v_fast (20cr).

project_id: put the clip into a project made with create_project instead of the
account's default one — one project per end client keeps their work separate.

Video generation routinely takes 1-3+ minutes, so this almost always returns
a job_id rather than a finished result — call check_job with it, waiting a
few seconds between checks, until status is 'done' or 'failed'.
beats: how many DISTINCT action phases the prompt describes — "ears flick back",
"tail lashes", "strikes the ball", "ball flies off" are four. Give it and the server
picks the clip length for you (about two phases per second) and says in the reply what
it picked and why. Measured 31.08.2026: the model STRETCHES whatever you describe over
whatever length you ask for, so one phase in four seconds comes out as slow motion, and
the same text at six seconds instead of four loses 15% of its movement. Adjectives are
not phases: "springy cartoon motion" adds nothing. Leave beats out and the length you
passed is used unchanged.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
beatsNo
aspectNoVIDEO_ASPECT_RATIO_LANDSCAPE
promptYes
project_idNo
include_previewNo
video_model_keyNoabra_t2v_4s

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say non-read-only, non-idempotent, non-destructive, so behavior is mostly undisclosed. The description compensates with concrete latency expectations (1-3+ minutes), the async job_id flow, credit costs per model, and a measured warning about how the model stretches motion over the requested length.

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 description is long but dense and front-loaded with the purpose before model options. The extended beats paragraph could be tightened, yet every sentence carries behavior the agent needs (definition, default, measured warning, exclusion of adjectives), so nothing is 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?

For a no-output-schema tool with 6 params, it covers the non-obvious behavior: async job_id, polling, credits, beats semantics, and project scoping. It doesn't explain the full 12-value model enum or include_preview's effect, which are minor gaps; the agent can still call the tool correctly using defaults.

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 0%, so the description carries the burden. It goes beyond the schema for video_model_key (credit costs and quality tiers), project_id (per-client separation), and beats (definition, examples, measured behavior). It leaves aspect and include_preview unexplained, but those are self-describing enums/booleans.

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?

Opens with a specific verb and resource ('Generate a video from a text prompt'), which clearly separates it from siblings like generate_video_from_image and generate_video_between_frames. The mention of Google Flow/Veo adds useful context without obscuring the core action.

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?

A large portion of the description is practical guidance: use create_project to scope per client, expect a job_id and poll check_job, and supply beats to let the server choose clip length. It doesn't explicitly name sibling alternatives or say when not to use them, but the text-prompt scope plus these instructions give clear calling context.

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

All openFlow 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