gflow-cli

Overview Schema Source Related Servers Discussions Admin

gflow_generate_video

Generate videos with Google Flow's Veo model using text, image, or reference prompts. Choose aspect ratio, model, duration, and count to create clips and get the local file path.

Instructions

Generate a video using Google Flow's Veo model. Modes: t2v (text-to-video), i2v (image-to-video), r2v (reference-to-video). Aspects: 9:16, 16:9. Optional model (veo_lite/veo_fast/veo_quality/omni_flash), duration (seconds), and count select the Veo model, clip length, and batch size (CLI parity). The prompt supports @CharacterName mentions to tag saved project characters by name (resolves to referenceEntities). Reference a SAVED character via @Name; pass one-off ingredient images via reference_images. See docs/REFERENCE_STRATEGIES.md. Optional ui_mode ('classic'/'auto') verifies the classic editor pre-submit and aborts before spending credits if unreachable; 'agentic' is not supported for video. Returns the local file path to the generated video.

Input Schema

TableJSON Schema

Name	Required	Default
`mode`	No	t2v
`wait`	No
`count`	No
`model`	No
`tools`	No
`aspect`	No	9:16
`output`	No
`prompt`	Yes
`profile`	No	default
`project`	No
`ui_mode`	No
`duration`	No
`end_frame`	No
`resolution`	No
`project_name`	No
`initial_frame`	No
`reference_images`	No
`reference_entities`	No
`reference_entity_names`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.79.1Sep 24, 2026

addedInput schema / properties / resolution

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Resolution"
+}

First observedSep 15, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full transparency burden. It discloses model selection behavior, character-reference resolution, credit-abort behavior when the classic editor is unreachable, and the fact that a local file path is returned. It does not cover every side effect or auth dependency, but it is substantially more transparent than typical tool descriptions.

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 front-loaded with the core purpose and then packs relevant details into a single dense paragraph. Every sentence adds information, including the docs pointer and the unsupported-mode caveat. It could be lightly restructured for readability, but it is appropriately sized and free of filler.

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 19-parameter tool with no schema descriptions and no annotations, the description covers the main workflow well but not the full surface. It explains output location and some safety behavior, and an output schema exists, but the many unelaborated optional parameters weaken overall completeness. An agent could call it for common cases but would be guessing on several advanced options.

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 0%, so the description must compensate; it meaningfully explains mode, aspect, model, duration, count, prompt, reference_images, and ui_mode. However, many of the 19 parameters such as wait, tools, output, profile, project, resolution, initial_frame, end_frame, reference_entities, and reference_entity_names are left unexplained beyond their parameter names. This is a notable gap for a large parameter surface.

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?

The description opens with a specific verb and resource: 'Generate a video using Google Flow's Veo model.' It enumerates modes, aspect ratios, and model choices, making its scope clear and distinct from sibling tools like gflow_generate_image. The naming and level of detail leave no ambiguity about what this 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?

The description gives practical guidance on when to use different sub-features: t2v, i2v, and r2v modes, saved-character mentions versus one-off reference images, and ui_mode constraints. It also explicitly notes that 'agentic' is unsupported for video. It does not directly compare itself to image generation or other sibling tools, but the intended usage context is clear.

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

Deploy Server