google-flow-mcp

Overview Schema Source Related Servers Discussions Admin

flow_generate_video

Generate videos with native audio from a text prompt using controls for duration, aspect ratio, resolution, camera moves, and image inputs to keep characters consistent.

Instructions

Generate a video with native audio using Gemini Omni Flash.

Args: prompt: Scene, camera movement, lighting, mood, sound. Say "single continuous shot" if you do not want cuts. duration_seconds: 3-15 (3-10 when last_frame_path is given). aspect_ratio: '16:9' or '9:16'. Overrides preset. resolution: '360p', '720p' (default), '1080p' or '4k' (1080p/4k are upscaled). preset: e.g. 'shorts' (9:16) or 'youtube-thumbnail' (16:9). camera: Camera move preset ('push-in', 'orbit', 'drone', 'handheld', ... see flow_list_presets) or your own description. negative_prompt: Things to avoid (e.g. "no dialogue, no text"). anchor_frame_path: Image to start from (image-to-video). last_frame_path: Image to end on (needs anchor_frame_path; interpolation). reference_image_paths: Up to 6 images of characters/objects to keep consistent. confirm_cost: Set true only after the user accepted the cost estimate. output_dir: Override the output folder. enhance_prompt: Ignored. Kept for compatibility with 0.1.0.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "flow_generate_video"
  }
}

Input Schema

Name	Required	Default
`camera`	No
`preset`	No
`prompt`	Yes
`output_dir`	No
`resolution`	No	720p
`aspect_ratio`	No
`confirm_cost`	No
`enhance_prompt`	No
`last_frame_path`	No
`negative_prompt`	No
`duration_seconds`	No
`anchor_frame_path`	No
`reference_image_paths`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.3Nov 13, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose genuinely useful behavior: a cost-confirmation gate via confirm_cost, the fact that 1080p/4k are upscaled rather than native, and a duration ceiling that shrinks when last_frame_path is used. It omits whether generation is long-running/blocking, what is returned (a file path?), and where output lands by default.

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?

Docstring-style argument list is dense with zero filler, and the one-sentence purpose leads. Ordering follows the schema rather than importance, so critical items like confirm_cost sit near the bottom, but no line is wasted.

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 13-parameter, no-annotation, no-output-schema tool this covers the parameter surface thoroughly, including the cost gate and the enhance_prompt deprecation note. The remaining hole is the return contract and execution model (single call vs. polling), which nothing else in the definition supplies.

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 description coverage is 0%, so the description must compensate across 13 parameters, and it largely does: accepted aspect ratios, resolution values with an upscaling caveat, duration ranges, preset examples, camera preset names plus a pointer to flow_list_presets, the 6-image cap on reference_image_paths, and the anchor/last-frame interpolation dependency. Defaults (8s duration, confirm_cost=false) and the format of output_dir are not spelled out.

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+resource ('Generate a video with native audio') plus the underlying model, which is more informative than the name alone. It does not differentiate itself from siblings like flow_image_to_video or flow_extend_video even though the anchor_frame_path/last_frame_path parameters overlap with their territory.

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?

Offers guidance inside individual arguments (use 'single continuous shot' to avoid cuts, pointer to flow_list_presets for camera presets, set confirm_cost only after the user accepts the estimate), which implies a workflow. It never states when to choose this tool over flow_image_to_video, flow_extend_video, or flow_edit_video, so sibling selection is left to inference.

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