Skip to main content
Glama
DarthAdry

Google Flow Browser MCP

by DarthAdry
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

flow_generate_image

Prepare and optionally generate images in Google Flow using Nano/Banana models. Default mode fills prompt and selects settings without consuming credits; auto-confirm verifies and triggers generation.

Instructions

⚠️ THESE IMAGES CONSUME CREDITS. By default (auto_confirm=false): fills the prompt, selects model/ratio, takes a screenshot and returns "ready_for_confirmation". Does NOT click Generate. When auto_confirm=true: first verifies the UI is in IMAGE mode (not Video), that the model is an image model, takes a verification screenshot, THEN clicks Generate and waits for the images. NANO/BANANA image models only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoModel to use: Nano Banana Pro, Nano Banana 2, or Imagen 4.Nano Banana 2
ratioNoAspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4.1:1
promptYesThe text prompt for image generation.
campaignNoCampaign identifier for project matching (e.g., "summer-2026", "new-collection").
use_sceneNoName of a single project scene to reference via "@name" (added in addition to ingredients).
ingredientsNoNames of existing project images/characters to reference via "@name" (e.g., ["Bob the Astronaut", "Image 3"]). Use flow_list_mention_options to discover available names.
auto_confirmNo⚠️ CREDITS. If false (default): only prepares, consumes nothing. If true: verifies that Image mode is active, THEN clicks Generate (consumes credits).
project_nameNoName for the project (will reuse existing project with same campaign, or create new).
use_characterNoName of a single project character to reference via "@name" (added in addition to ingredients).
reference_imagesNoPaths to local reference images to upload (optional).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.5/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden and does so well: it discloses credit consumption, the exact steps taken in each mode (fill prompt, select model/ratio, screenshot, return 'ready_for_confirmation'), that Generate is NOT clicked by default, the pre-flight verification of mode and model, and the wait-for-images behavior. This is far richer than a typical schema would convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The credit warning is front-loaded, and the two modes are laid out as parallel clauses rather than repetition. Density is high with virtually no filler despite covering a complex flow.

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?

For a 10-parameter, side-effectful generation tool with no annotations and no output schema, the description covers the critical unknowns: cost implications, what is and isn't executed per mode, and the partial return value ('ready_for_confirmation'). Nothing essential to safe invocation is missing.

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 every parameter is already documented with defaults, formats, and examples. The description reinforces auto_confirm's semantics but adds no parameter meaning beyond the schema. Baseline 3 is appropriate.

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 (generate image) and explicitly scopes the model family ('NANO/BANANA image models only'), which cleanly separates it from sibling flow_generate_video. The two-mode behavior is front-loaded so an agent knows immediately what the tool does.

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 contrasts the two operating modes: auto_confirm=false prepares only, auto_confirm=true verifies and clicks Generate. It also specifies prerequisites (UI must be in IMAGE mode, model must be an image model). It does not name sibling alternatives for video generation, but the scoping note covers the main branch point.

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