Skip to main content
Glama

gflow_generate_video

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.

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/omni_1_2_flash), duration (seconds; omni_1_2_flash takes 3-15, at most 10 with an end_frame), 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; on flow.google.com a video @Name is not supported yet, exit 29 before submit, so pass reference_entities plus reference_entity_names to r2v). 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. out_file, if given, must resolve inside the configured output directory. Returns the local file path to the generated video.

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": "gflow_generate_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNot2v
waitNotrue (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, or use false. false: return {status: 'pending', task_id} at once and run the job in the background of this server process. With the SEP-2663 Tasks extension, poll tasks/get by task_id: while it runs the status is working; once done it is completed and its result field holds the same reply wait=true would (files, project id, seed). A failed generation is also completed, with result.isError true, so check isError. tasks/cancel aborts the job locally; tasks/get then reads cancelled. A job not yet submitted to Flow stops before submitting and nothing is charged; once a gflow worker has submitted it, Flow cannot cancel it, so it may still be charged (statusMessage says which). gflow cancel <id> is the CLI twin. The job runs only while this server runs: if the client closes the server, it is cancelled.
countNo
modelNo
toolsNoPrompt tools applied before generation. Each item is {"name": <slug>, "options": {...}}, e.g. [{"name": "creative-director"}]. gflow_list_tools lists the valid names.
aspectNo9:16
promptYes
profileNodefault
projectNo
ui_modeNo
durationNo
out_fileNoOptional file to write, inside the configured output dir: a relative path is taken relative to it; an escape or a directory is refused.
end_frameNo
resolutionNo
project_nameNo
initial_frameNo
reference_imagesNo
reference_entitiesNoSaved character entity ids to attach. On flow.google.com each id needs its display name at the same position in reference_entity_names, or the call fails before submit; gflow_character_list returns both. Character references need mode r2v there.
reference_entity_namesNoDisplay name of each reference_entities id, same order. Required on flow.google.com, where an id without its name fails before submit.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.101.0
    • addedInput schema / properties / out_file
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional file to write, inside the configured output dir: a relative path is taken relative to it; an escape or a directory is refused.",
      +  "title": "Out File"
      +}
    • removedInput schema / properties / output
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Output"
      -}
    • changedInput schema / properties / reference_entities / description
      Previous value: -"Saved character entity ids to attach. On flow.google.com each id needs its display name at the same position in reference_entity_names, or the call fails before submit; gflow_character_list returns both (if it fails with a wire-format error, #875, ask the user or read the name in Flow's UI). Character references need mode r2v there."New value: +"Saved character entity ids to attach. On flow.google.com each id needs its display name at the same position in reference_entity_names, or the call fails before submit; gflow_character_list returns both. Character references need mode r2v there."
    • changedInput schema / properties / wait / description
      Previous 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, or use false. false: return {status: 'pending', task_id} at once and run the job in the background of this server process. With the SEP-2663 Tasks extension, poll tasks/get by task_id: while it runs the status is working; once done it is completed and its result field holds the same reply wait=true would (files, project id, seed). A failed generation is also completed, with result.isError true, so check isError. tasks/cancel stops the job; tasks/get then reads cancelled (a job cancelled after submit is recorded as indeterminate: a credit may be spent). The job runs only while this server runs: if the client closes the server, it is cancelled."New 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, or use false. false: return {status: 'pending', task_id} at once and run the job in the background of this server process. With the SEP-2663 Tasks extension, poll tasks/get by task_id: while it runs the status is working; once done it is completed and its result field holds the same reply wait=true would (files, project id, seed). A failed generation is also completed, with result.isError true, so check isError. tasks/cancel aborts the job locally; tasks/get then reads cancelled. A job not yet submitted to Flow stops before submitting and nothing is charged; once a gflow worker has submitted it, Flow cannot cancel it, so it may still be charged (statusMessage says which). gflow cancel <id> is the CLI twin. The job runs only while this server runs: if the client closes the server, it is cancelled."
  2. Changed1 schema field changedv0.92.1
    • changedInput schema / properties / reference_entities / description
      Previous value: -"Saved character entity ids to attach. On flow.google.com each id needs its display name at the same position in reference_entity_names, or the call fails before submit; gflow_character_list returns both (if it exits 7, #875, ask the user or read the name in Flow's UI). Character references need mode r2v there."New value: +"Saved character entity ids to attach. On flow.google.com each id needs its display name at the same position in reference_entity_names, or the call fails before submit; gflow_character_list returns both (if it fails with a wire-format error, #875, ask the user or read the name in Flow's UI). Character references need mode r2v there."
  3. Changed3 schema fields changedv0.92.0
    • addedInput schema / properties / reference_entities / description
      Added value: +"Saved character entity ids to attach. On flow.google.com each id needs its display name at the same position in reference_entity_names, or the call fails before submit; gflow_character_list returns both (if it exits 7, #875, ask the user or read the name in Flow's UI). Character references need mode r2v there."
    • addedInput schema / properties / reference_entity_names / description
      Added value: +"Display name of each reference_entities id, same order. Required on flow.google.com, where an id without its name fails before submit."
    • addedInput schema / properties / tools / description
      Added value: +"Prompt tools applied before generation. Each item is {\"name\": <slug>, \"options\": {...}}, e.g. [{\"name\": \"creative-director\"}]. gflow_list_tools lists the valid names."
  4. Changed1 schema field changedv0.91.0
    • changedInput schema / properties / wait / description
      Previous 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."New 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, or use false. false: return {status: 'pending', task_id} at once and run the job in the background of this server process. With the SEP-2663 Tasks extension, poll tasks/get by task_id: while it runs the status is working; once done it is completed and its result field holds the same reply wait=true would (files, project id, seed). A failed generation is also completed, with result.isError true, so check isError. tasks/cancel stops the job; tasks/get then reads cancelled (a job cancelled after submit is recorded as indeterminate: a credit may be spent). The job runs only while this server runs: if the client closes the server, it is cancelled."
  5. Changed1 schema field changedv0.90.0
    • 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."
  6. Changed1 schema field changedv0.79.1
    • addedInput schema / properties / resolution
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Resolution"
      +}
  7. First observed

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 burden well: it discloses credit-spending risk and that ui_mode='classic'/'auto' aborts pre-submit if the editor is unreachable, that @Name video references exit with code 29 before submit, and that out_file must resolve inside the output directory. It also states the return value is the local file path. It omits auth/profile requirements and rate or concurrency limits.

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

Conciseness3/5

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

The purpose and mode list are front-loaded, which is good, but the body becomes a dense run-on of parenthetical asides (CLI parity, flow.google.com caveats, docs pointer) that are hard to scan. The information is mostly valuable, but the wall-of-text packaging makes it slower to parse than it needs to be.

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 19-parameter generation tool with no annotations, the definition covers the decision-critical surface: modes, references, credit-abort behavior, file output constraints, and the return value, with an output schema available for the reply shape. The remaining gaps are the seven undocumented secondary parameters, which are mostly advanced or defaulted settings.

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 26% across 19 parameters, so the description must compensate. It explains mode, aspect, model, duration (including the 3-15 range and the 10-second cap with an end_frame), count, @CharacterName prompt syntax, reference_images vs reference_entities/reference_entity_names, ui_mode, and out_file. However it is silent on wait, tools, profile, project, project_name, resolution, and initial_frame, leaving several parameters documented nowhere.

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 immediately distinguishes itself from siblings by enumerating its generation modes (t2v/i2v/r2v), which clearly separates it from gflow_generate_image and gflow_upscale_video without the agent needing to open another schema.

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?

It gives real routing guidance: which mode to pick for text vs image vs reference input, the constraint that character references need r2v on flow.google.com, and pointers to gflow_character_list for ids/names and gflow_list_tools for prompt-tool slugs. It does not explicitly exclude or defer to other generation tools, so it stops short of a full alternatives statement.

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