Skip to main content
Glama

photo_crop

Crop Image — Crop an image to a specified region (x, y, width, height) in pixels. [category: photo]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoLeft offset px on the DISPLAYED (EXIF-upright) image — the handler auto-orients before cropping.
yNoTop offset px on the DISPLAYED (EXIF-upright) image — the handler auto-orients before cropping.
fileYesJPG, PNG, WebP, HEIC, TIFF, BMP, or GIF. Output keeps the input format, except that a HEIC or HEIF photo comes back as a JPG.
widthYesCrop width px. Clipped at the image edge if the region overruns.
heightYesCrop height px. A region overrunning the image edge is clipped, not an error.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / height / x-ui / draw
      Added value: +{
      +  "of": "crop",
      +  "role": "height"
      +}
    • addedInput schema / properties / width / x-ui / draw
      Added value: +{
      +  "of": "crop",
      +  "role": "width"
      +}
    • addedInput schema / properties / x / x-ui / draw
      Added value: +{
      +  "of": "crop",
      +  "role": "left"
      +}
    • addedInput schema / properties / y / x-ui / draw
      Added value: +{
      +  "of": "crop",
      +  "role": "top"
      +}
    • addedInput schema / x-draw
      Added value: +{
      +  "crop": {
      +    "noun": "crop box",
      +    "shape": "box",
      +    "title": "Part to keep"
      +  }
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / x / x-ui / pair_joint
      Added value: +","
  3. Changed4 schema fields changed
    • addedInput schema / properties / width / x-ui / pair_label
      Added value: +"Size"
    • addedInput schema / properties / width / x-ui / pair_with
      Added value: +"height"
    • addedInput schema / properties / x / x-ui / pair_label
      Added value: +"Top-left corner"
    • addedInput schema / properties / x / x-ui / pair_with
      Added value: +"y"
  4. Changed1 schema field changed
    • changedInput schema / properties / file / description
      Previous value: -"JPG, PNG, WebP, HEIC, TIFF, BMP, or GIF. Output keeps the input format."New value: +"JPG, PNG, WebP, HEIC, TIFF, BMP, or GIF. Output keeps the input format, except that a HEIC or HEIF photo comes back as a JPG."
  5. Changed4 schema fields changed
    • addedInput schema / properties / height / x-ui
      Added value: +{
      +  "unit": "px"
      +}
    • addedInput schema / properties / width / x-ui
      Added value: +{
      +  "unit": "px"
      +}
    • addedInput schema / properties / x / x-ui
      Added value: +{
      +  "unit": "px"
      +}
    • addedInput schema / properties / y / x-ui
      Added value: +{
      +  "unit": "px"
      +}
  6. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the bar is lowered and the safety profile is already disclosed. The description adds only that the region is in pixels, offering no behavioral detail of its own; richer traits like EXIF auto-orientation and edge clipping live in the schema, not the description.

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?

A single compact sentence plus a category tag, with the action and the region tuple front-loaded. Nothing is wasted, though the trailing '[category: photo]' tag adds little value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so return-value explanation is not strictly required, and the schema is unusually rich. However, the description omits usage context and any behavioral framing beyond pixels, so it is only minimally complete for an agent deciding whether and how to call it.

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%, so the schema already documents every parameter in depth (EXIF-upright handling, clipping behavior, format preservation). The description merely restates the four coordinate/box parameters, adding no semantics beyond what the schema provides, which is the baseline-3 case.

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 (Crop) plus resource (image) and the exact region parameters (x, y, width, height) in pixels, so the operation is unambiguous. It does not differentiate itself from closely related siblings such as photo_resize, photo_image_splitter, or pdf_crop, keeping it at a 4 rather than a 5.

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

Usage Guidelines2/5

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

The description gives no when-to-use guidance, no prerequisites, and no alternatives. An agent cannot infer from the text whether to reach for photo_crop versus photo_resize or photo_image_splitter; usage is only implied by the tool name.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources