Skip to main content
Glama

gflow_upscale_video

Upscale or export a platform-generated Flow video to 1080p Full HD, or convert it to a 270p animated GIF, using its media ID.

Instructions

Upscale or export a platform-generated Flow video to 1080p Full HD (or 270p GIF). media_id is the UUID of the video to upscale. scale is '1080p' (Full HD), '720p' (original), or '270p' (animated GIF). project is optional (resolved from the local catalog when omitted). out_dir is the output directory (defaults to configured videos directory; must resolve inside the configured output directory). profile selects the auth profile (defaults to the active profile). flow.google.com only (GFLOW_CLI_FLOW_HOST=labs.google refuses it). Measured free (1 observation, 2026-10-07): the 1080p export spent no credits.

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": {
      "media_id": "<media_id>"
    },
    "name": "gflow_upscale_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
scaleNo1080p
out_dirNo
profileNodefault
projectNo
media_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.83.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations, so the description carries the full burden and does well: it discloses host refusal behavior, that out_dir 'must resolve inside the configured output directory' (a failure mode), and even a dated cost observation ('measured free, 1 observation'). Caveat: the cost claim is hedged to a single observation and no error/overwrite semantics are given.

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 action and output, then parameter-by-parameter, then constraints and cost. Dense but nearly every clause carries information; the parenthetical host-variable spelling is slightly verbose, though operationally useful.

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?

An output schema exists so return values needn't be explained, and all five parameters plus the cost and host constraints are covered. Missing only edge behavior an agent might hit: what happens if media_id is not an already-generated Flow video, and whether an existing output file is overwritten.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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 does: media_id is defined as the video UUID, scale enumerates all three values with meanings ('1080p' Full HD, '720p' the original, '270p' animated GIF — a detail absent from the schema, which has no enum), and project/out_dir/profile each get defaults and resolution rules.

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 and resource ('Upscale or export a platform-generated Flow video') and immediately qualifies the outputs (1080p Full HD or 270p GIF). The 'platform-generated Flow video' scoping plus the sibling set (gflow_upscale_image, gflow_generate_video) makes it unambiguous which tool handles video upscaling.

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 a clear applicability constraint — 'flow.google.com only (GFLOW_CLI_FLOW_HOST=labs.google refuses it)' — which is exactly the kind of when-not context agents need. It does not explicitly contrast with gflow_upscale_image or gflow_download_media, but the resource type makes that routing self-evident.

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