google-flow-mcp

Overview Schema Source Related Servers Discussions Admin

flow_generate_narration

Generate Gemini TTS voice-overs from text in 130+ languages, add inline pause or laugh tags, and attach the result to a project for film assembly.

Instructions

Generate a voice-over with Gemini TTS (130+ languages, including Korean; very cheap).

Inline tags such as , or are supported. In a project the narration is laid over the film from the start by flow_assemble.

Args: text: The words to speak. voice: Prebuilt voice, e.g. Kore (firm), Puck (upbeat), Charon (informative), Aoede (breezy), Sulafat (warm), Achird (friendly), Gacrux (mature). style: Delivery, e.g. 'calm documentary narrator' or 'excited, fast'. attach: Store it as the active project's narration. project_name: Project to use (default: active project, if any).

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": {
      "text": "<text>"
    },
    "name": "flow_generate_narration"
  }
}

Input Schema

Name	Required	Default
`text`	Yes
`style`	No
`voice`	No	Kore
`attach`	No
`project_name`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.3Nov 13, 2026

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose non-obvious behavior (inline tags are honored, attach=true stores the clip as the active project's narration, flow_assemble overlays it from the start), but never says what is returned (file path, asset id, duration) or whether generation is slow or billed per call.

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?

Front-loaded with the core purpose, then tags, then composition context, then the Args block. The docstring format is slightly verbose and partly restates schema titles, but nearly every line 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 generation tool with no output schema and no annotations, the description should say what the caller receives back and whether the artifact persists when attach is false. The project/flow_assemble coupling is covered, but return-value semantics are not.

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 coverage is 0%, so the description must carry parameter meaning, and it does: all five params are explained, including concrete voice presets with tonal descriptors, style examples, attach semantics, and the default-project behavior. Missing only constraints such as text length limits or whether style overrides voice character.

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 a voice-over) plus the engine (Gemini TTS) and scope (130+ languages), which cleanly separates it from siblings like flow_generate_music or flow_generate_video. An agent can identify the operation without opening the schema.

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?

Usage is only implied: you learn that inline tags work and that in a project the narration is laid over the film from the start by flow_assemble, which is a useful downstream relationship. There is no explicit when-to-use, when-not-to-use, or alternative-selection guidance.

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