Skip to main content
Glama
DarthAdry

Google Flow Browser MCP

by DarthAdry
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

flow_generate_video

Prepare Veo video drafts from prompts, shots, or ingredients without spending credits; verify and optionally click Generate for paid rendering with chosen duration, ratio, quality, and references.

Instructions

Prepare a Veo video (prepare-only, no spend). Fast tests, Quality finals; ingredients need 8s.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoVideo model name — call flow_list_models for the live list — or auto.auto
ratioNo16:9 or 9:16.16:9
shotsNoMulti-shot plan, max 6: [{prompt, duration}].
styleNoLook/mood/lighting. No extra subjects in refs.
cameraNoCamera move: push-in, pull-back, pan, tilt, orbit, tracking shot.
promptYesScene + action. Optics stay in UI selectors.
qualityNoResolution 360p/720p.
campaignNoCampaign id (doubles as project name when name absent).
durationNo4s, 6s, 8s, 10s. Ingredients force 8s.4s
quantityNoVariants 1-4 for compare-pick-refine.
end_frameNoLast-frame image path. Shares light/framing with start.
use_sceneNoName of a single project scene to reference via "@name" (added in addition to ingredients).
hero_frameNoAlias for start_frame.
ingredientsNoProject images/characters to reference via "@name" (e.g., ["Bob the Astronaut", "Image 3"]). Discover names via flow_list_mention_options.
project_urlNoDirect Flow /project/ URL — wins over name matching.
start_frameNoFirst-frame image path (hero frame anchor).
anchor_frameNoPrior strongest frame carried for continuity.
auto_confirmNoAlways prepare-only today. Reserved.
project_nameNoProject name (remembered; reopens instead of duplicating).
use_characterNoName of a single project character to reference via "@name" (added in addition to ingredients).
confirm_generateNoLIVE PAID CLICK: verify, click Generate (credits), poll video. Default false.
reference_imagesNoPaths to local reference images to upload (optional).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses the default no-spend prepare behavior, which counteracts the misleading 'generate' name, but it says nothing about the paid confirm_generate path, required auth, or polling/credit consumption beyond what the schema param already states.

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?

Three front-loaded fragments lead with the single most important behavior (prepare-only, no spend) and waste no words. The terseness makes 'Fast tests, Quality finals' slightly cryptic, but nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 22-parameter, annotation-free tool with no output schema, the description covers the core safety profile but is thin on the surrounding workflow (how it pairs with flow_list_models, flow_list_mention_options, or the confirm/poll path). The rich schema compensates for parameters, but behavioral coverage is minimal.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all 22 parameters are already documented, giving a baseline of 3. The description adds only a marginal cross-parameter rule ('ingredients need 8s', quality tiers) beyond what the individual param descriptions already say.

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?

States a specific verb (Prepare) and resource (Veo video) and immediately disambiguates against its own name by noting 'prepare-only, no spend'. An agent can tell it produces a video plan rather than a video, though it never names the sibling flow_generate_image or explains how it relates to the image tool.

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?

'Fast tests, Quality finals' implies a quality-tier decision and 'ingredients need 8s' gives a conditional constraint, but there is no explicit when-to-use vs alternatives, no exclusion of the live-generate path, and no prerequisites (auth, project) stated.

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

Deploy Server

Other Tools