gflow-cli

Overview Schema Source Related Servers Discussions Admin

gflow_generate_video

Generate videos from text, images, or saved character references using Google Flow's Veo model. Choose aspect ratio, model, duration, and batch count, then return the local video 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

Name	Required	Description	Default
`mode`	No		t2v
`wait`	No	true (default): run the generation inside this call and return the finished result. The call stays open for the whole generation, minutes for a video, which can outlast an MCP client's tool timeout; raise that timeout for generation calls. false: only enqueue the job and return {status: 'pending', task_id} at once; the SEP-2663 Tasks extension's tasks/get reads its state by task_id. No gflow command runs the queue worker today, so a wait=false job is never generated: tasks/get reports it as 'working' indefinitely, and tasks/cancel clears it. Use the default.
`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

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.90.0Oct 25, 2026

addedInput schema / properties / wait / description

Added value: +"true (default): run the generation inside this call and return the finished result. The call stays open for the whole generation, minutes for a video, which can outlast an MCP client's tool timeout; raise that timeout for generation calls. false: only enqueue the job and return {status: 'pending', task_id} at once; the SEP-2663 Tasks extension's tasks/get reads its state by task_id. No gflow command runs the queue worker today, so a wait=false job is never generated: tasks/get reports it as 'working' indefinitely, and tasks/cancel clears it. Use the default."

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

A3.8/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It adds genuinely useful behavior: credit spend risk, abort-before-spend verification, @mention resolution to referenceEntities, and that it returns a local file path. However it omits the long-running blocking nature of generation (documented only in the `wait` schema field), which is the single most important behavioral trait for an agent calling this.

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?

Dense, telegraphic and front-loaded with the core action and modes before detail. The middle is packed into long comma-chained clauses, which is efficient but slightly harder to parse than it could be; every sentence still carries information.

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 annotations, several parameters remain opaque (project identity, frames, resolution, tools), and the blocking/timeout behavior of a default `wait=true` video generation is not surfaced in the description itself. It is adequate to call the tool for the happy path but incomplete for confident use of the full schema.

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 coverage is only 5% across 19 parameters. The description compensates for roughly half — mode, aspect, model names, duration, count, prompt @mentions, reference_images, ui_mode — but leaves `project` vs `project_name` vs `profile`, `initial_frame`/`end_frame`, `resolution`, `tools`, and `reference_entities`/`reference_entity_names` unexplained in both places.

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 using Google Flow's Veo model', then enumerates the three generation modes. It is unmistakably distinct from the sibling gflow_generate_image and from the character/instructions tools.

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?

Gives concrete routing guidance between saved characters (@Name) and one-off ingredient images (reference_images), and explains when ui_mode='classic' is worth setting (pre-submit verification to avoid wasting credits). It never explicitly contrasts with a sibling tool or states when not to use it, so it falls short of a 5.

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