Skip to main content
Glama
Sign In
video-analyzer

video-analyzer

by thomasbrosch
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

analyze_video

Analyze video ad creatives to gain actionable insights. This tool delivers scene-by-scene breakdowns, transcripts, and performance signals to inform iteration and optimization.

Instructions

Analyze video ad creatives using Gemini's native video understanding. Accepts a single video file path or a directory of videos. Returns a structured creative breakdown including scene-by-scene analysis, transcript, performance signals, and iteration briefs. Supports: .3gp, .avi, .flv, .m4v, .mkv, .mov, .mp4, .mpeg, .mpg, .webm, .wmv

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": "analyze_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath to a video file or a directory containing video files. If a directory, all supported video files in it will be analyzed.
modelNoGemini model to use. 'flash' (gemini-2.5-flash) is fast and cheap — good for batch processing. 'pro' (gemini-2.5-pro) is more capable — good for deep single-video analysis.flash
output_dirNoOptional directory to save analysis as markdown files. Each video gets a separate _analysis.md file.
custom_promptNoOptional custom analysis prompt. If not provided, uses the default ad creative analysis prompt covering creative structure, performance signals, and iteration briefs.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does useful work by disclosing the output content and the set of supported file extensions, but it omits material behavior for a Gemini-backed, potentially long-running batch job: cost/latency characteristics, whether directories are traversed recursively, and what happens to unsupported or failing files.

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 action and return artifacts, then scope, then formats. The extension list is bulky but earns its place by defining what counts as an analyzable video; the only redundancy is restating single-file vs directory, which the schema already covers.

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 need not be spelled out, yet the description summarizes them helpfully. Combined with a fully documented schema, an agent has enough to call it correctly; missing only operational caveats like runtime, cost, and recursive directory behavior.

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 description coverage is 100% and the model, output_dir, and custom_prompt parameters already have thorough inline docs, so the schema does the heavy lifting. The description adds only the supported-format list, which marginally informs which files a directory path will pick up.

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 specific verb (analyze) plus a specific resource (video ad creatives) and enumerates the artifacts produced: scene-by-scene analysis, transcript, performance signals, iteration briefs. It never references the sibling list_videos, but the tool's purpose is distinct enough that confusion is unlikely.

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?

"Accepts a single video file path or a directory of videos" implies when the tool is applicable (batch vs single) but gives no explicit when-to-use/when-not guidance and mentions no alternatives. Usage must be inferred from the input shape rather than stated.

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

Deploy Server

Other Tools