Skip to main content
Glama

Inspect part of an image at full resolution

inspect_image

Inspect any region of a gallery image or video preview at full resolution (up to 1024 px) to verify hands, faces, products, and lettering before animating.

Instructions

Returns a region of a gallery image (or a video's preview frame) at full resolution, up to 1024 px. The previews from generate are only 512 px; use this to check hands, faces, products and lettering before animating. Region as fractions of the image: x, y = top-left corner, w, h = size (0 to 1). Default: the whole image.

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": {
      "id": "<id>"
    },
    "name": "inspect_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
hNo
wNo
xNo
yNo
idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose key behavior: the returned region is capped at 1024 px, the previews from `generate` are 512 px, and the default is the whole image. It does not state the return format (inline image vs. a reference/URL) or any cost or rate considerations for full-resolution reads, which is the main remaining gap.

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?

Three tight sentences: what it returns first, then the practical reason and the comparison to `generate` previews, then the region coordinate convention and default. Nothing is repeated and the most important facts are front-loaded.

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 read-only tool with five simple parameters and no output schema, the description covers the return semantics and coordinate system well enough to call it correctly. The notable omissions are what `id` refers to and how the image region is delivered back, which an agent would still need to discover by other means.

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% and there are five parameters, so the description must compensate and it largely does: x, y are defined as the top-left corner and w, h as the size, all as fractions from 0 to 1, with the default described as the whole image. The `id` parameter is never explained (presumably the gallery image identifier), leaving one of five parameters undocumented in both places.

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?

The description opens with a specific verb-plus-resource: 'Returns a region of a gallery image (or a video's preview frame) at full resolution.' It further distinguishes the tool from the `generate` previews by naming the 512 px vs 1024 px difference, so an agent can tell it apart from siblings without inspecting any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states the use case and timing: 'use this to check hands, faces, products and lettering before animating,' and frames it against the alternative of relying on lower-resolution previews from `generate`. That names the alternative and the condition that selects this tool, leaving little to inference.

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