google-flow-mcp

Overview Schema Source Related Servers Discussions Admin

flow_review

Inspect generated images or sample video frames to visually verify faces, hands, text spelling, frame continuity, and prompt adherence before telling the user the result is good.

Instructions

Look at a generated file: returns the image, or evenly spaced frames of a video.

Use this to check a result with your own eyes before telling the user it is good: faces and hands, text spelling, continuity between frames, whether the prompt was followed.

Args: path: Image or video file. frames: Number of video frames to sample (1-12, default 6).

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": {
      "path": "<path>"
    },
    "name": "flow_review"
  }
}

Input Schema

Name	Required	Description	Default
`path`	Yes
`frames`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.3Nov 13, 2026

TDQS

A4.1/5.0

Behavior4/5

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

No annotations exist, so the description carries the full burden and does well: it discloses the return shape (a single image or N sampled frames) and the sampling behavior, implying a safe read-only inspection. It omits things like file-size limits, cost, or what happens on an unsupported or missing path.

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

Conciseness5/5

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

Front-loaded with the core action, then the when-to-use rationale, then terse per-argument notes. Every line earns its place and the checklist is stated compactly.

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 two-parameter read-only inspection tool with no output schema, the description covers the return shape, the sampling control, and the review purpose. Only minor operational details (what path formats are accepted, error behavior) are missing.

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 compensate, and it does for both parameters: path is 'Image or video file', and frames is 'Number of video frames to sample (1-12, default 6)', adding a range constraint the schema lacks. It does not say whether frames is ignored for still images.

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 concrete verb and resource: it returns the image, or evenly spaced frames of a video, from a generated file. That separates it clearly from the generate/edit siblings, but it never names an alternative tool the way a 5 would.

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 an explicit when-to-use case: 'check a result with your own eyes before telling the user it is good', with a concrete checklist of what to look for (faces/hands, text spelling, frame continuity, prompt adherence). No exclusions or named alternatives, so it stops 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.