Skip to main content
Glama
KyaniteLabs

kinocut

by KyaniteLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

image_analyze_product

Extract dominant colors from a product image or video frame and optionally generate an AI description to support product analysis.

Instructions

Analyze a product image or video frame — extract colors and optionally generate AI description.

Extracts dominant colors locally. For provider-neutral descriptions, inspect the image with your host's configured vision model. The optional legacy description adapter uses the Anthropic-compatible Messages protocol and is disabled by default, even when an API key is present.

Args: image_path: Absolute path to the image or video file. If video, extracts a representative frame. use_ai: Request a legacy provider description. Also requires operator consent: KINOCUT_VISION_MODE=local with a loopback KINOCUT_VISION_BASE_URL, or remote for a hosted endpoint. Local endpoints need no API key. KINOCUT_VISION_MODEL selects the model; this adapter does not inherit host routing. n_colors: Number of dominant colors to extract (default 5).

Input Schema

NameRequiredDescriptionDefault
use_aiNo
n_colorsNo
overwriteNoExplicitly allow replacing existing media. Existing non-media files are protected.
image_pathYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.16.4
    • addedInput schema / properties / overwrite
      Added value: +{
+  "default": false,
+  "description": "Explicitly allow replacing existing media. Existing non-media files are protected.",
+  "title": "Overwrite",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv1.16.0
    • addedInput schema / additionalProperties
      Added value: +false
  3. Addedv1.5.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does it well: it discloses that color extraction is local, that the legacy description adapter is disabled by default even with an API key present, that it requires KINOCUT_VISION_MODE plus a loopback base URL, and that it does not inherit host routing. It does not describe failure behavior for bad paths or how video frames are chosen, 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 purpose and the key routing advice are front-loaded in the first two sentences, and the numbered Args section is easy to scan. The consent block is dense and slightly overlong relative to the size of the operation, but every sentence carries operational meaning.

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 explained, and the description covers the mutation/replace semantics only indirectly through the schema-documented overwrite flag. For a four-parameter tool with non-obvious provider gating, the description supplies what an agent needs to call it correctly.

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 only 25%, so the description must compensate, and it does: image_path is documented as an absolute path that also accepts video files (with representative-frame extraction), use_ai carries its full environment gating, and n_colors states the default and meaning. The one undescribed parameter, overwrite, is already documented in the schema.

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 first line gives a concrete verb+resource: analyze a product image or video frame, extracting colors and optionally an AI description. It is specific enough for an agent to know what it does, but it never distinguishes itself from close siblings such as image_extract_colors or image_generate_palette, leaving the agent to infer which of the three to pick.

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?

It explicitly routes the agent away from use_ai for provider-neutral descriptions ('inspect the image with your host's configured vision model'), and it states the operator-consent preconditions under which use_ai actually works. What's missing is any comparison to the color-extraction siblings, so the guidance covers context but not sibling selection.

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