Skip to main content
Glama

review_video

Samples a video into side-by-side frames in one image so you can check whether a generated clip worked, with optional vision-model scoring and problem detection.

Instructions

Shows you the clip: frames spread over it (start, middle, end for 3) side by side in ONE picture, after the start picture, so you can SEE if it worked. judge=true also asks a vision model for a score and problems (uses the Gemini/NVIDIA key from OpenDaemon). Look for: the character changing, the action not happening, extra hands, melting, the end falling apart.

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": {
      "video": "<video>"
    },
    "name": "review_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
judgeNo
videoYes
framesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Beyond annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) the description discloses important behavior: output is a single composited image, and judge=true makes an external vision-model call using the Gemini/NVIDIA key from OpenDaemon — a credentials/network dependency an agent needs to know. It does not say where the picture is written or whether repeated calls cost quota, which keeps it below 5.

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?

The key fact — one side-by-side picture — is front-loaded, and the sentences are short. The 'Look for:' list is practical rather than filler, though the conversational phrasing ('Shows you the clip', 'so you can SEE') is less efficient than a declarative statement.

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?

With no output schema, the description does the work of explaining the return: a single image with ordered frames, plus a score and problem list when judge=true. That is enough to call and interpret the tool; only the destination/format of the generated picture is left unstated.

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 carries the burden, and it does add real meaning: frames is explained as sample points (start/middle/end at 3) in one composite, and judge=true is explained as invoking a vision model for a score plus detected problems. The required 'video' parameter is left to the schema, which is a minor gap.

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?

The description states concretely what the tool produces: frames sampled across the clip (start, middle, end for frames=3) composited into one side-by-side picture so the result can be visually inspected. That is a specific verb+resource and clearly differs from siblings like video_info or build_video, though it never names an alternative to differentiate itself explicitly.

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 implied through 'so you can SEE if it worked' and the 'Look for:' checklist of failure modes (character changing, action not happening, extra hands, melting), which tells the agent this is a post-generation QA step. It does not say when to prefer this over video_info, when to set judge=true vs. eyeballing frames, or what the cost tradeoff of the vision model is.

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