Skip to main content
Glama

flow_generate_video

Generate videos from a text prompt on Google Flow: preview the job first with no credits spent, or confirm to render and download the MP4.

Instructions

⚠️ CONSUMA CREDITI FLOW (Veo/Omni). Con auto_confirm=false (default): prepara il prompt video e si ferma senza generare (nessun credito). Con auto_confirm=true: invia, attende il render (minuti) e scarica l'mp4. Modello economico per test: "lite" (Veo 3.1 Lite).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoModel: lite, fast (default), quality, flash (Omni 1.1 Flash), or the exact Flow name.fast
ratioNoAspect ratio: 16:9 or 9:16.16:9
promptYesThe text prompt for video generation.
campaignNoCampaign identifier for project matching.
durationNoDuration like "4s", "6s", "8s".4s
auto_confirmNo⚠️ CREDITI. false (default): prepara soltanto. true: genera davvero (consuma crediti Flow) e scarica.
project_nameNoName for the project (will reuse existing project with same campaign, or create new).
reference_imagesNoPaths to images the video must include as ingredients (optional).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does well: it warns that the tool consumes Flow credits, discloses that auto_confirm=true waits minutes for render, and that the result is a downloaded mp4. It omits failure behavior, rate limits, and any account/permission requirements, which is why it is not a 5.

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-loads the credit warning with a ⚠️ marker, then covers the two modes and the model hint in three tight sentences. There is minor redundancy with the auto_confirm parameter description already in the schema, but no wasted prose.

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 costly, non-read-only tool with no annotations and no output schema, the description adequately covers cost, mode behavior, timing, and the returned artifact (mp4). It stops short of covering failure modes and account/prerequisite setup, leaving a small gap.

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% with detailed per-parameter descriptions, so the baseline is 3. The description adds genuine value beyond the schema by explaining the auto_confirm workflow end-to-end and flagging 'lite' (Veo 3.1 Lite) as the economical model for testing, which the schema alone does not convey.

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 (generate video) and immediately distinguishes the two operating modes (auto_confirm false = prepare only, true = actually render and download). The video focus cleanly separates it from the sibling flow_generate_image.

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?

Explicitly tells the agent when to use each mode: false for a no-cost dry run, true to actually spend credits and download, plus a recommendation to use the cheap 'lite' model for testing. It does not, however, explain prerequisites (e.g., whether flow_connect is required first) or when to prefer flow_generate_image instead.

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