Skip to main content
Glama
Garden Design MCP Server

Garden Design MCP Server

zoom_image

Inspect attached images or survey maps up close to place survey and garden points precisely. Returns a zoomed view of the original around a chosen pixel coordinate.

Instructions

Look closer at an image the designer attached in the chat (e.g. a survey map) to place points precisely. Attached images arrive labelled "Image 1", "Image 2"…; each is a view ("1") in the pixels you see. Returns a close-up of the full-size original around a point of a view, as a new view ("1.1", "1.2"…) with its own pixels. Points for set_survey_map and map_to_garden are given on any view. Only in the editor's own chat, where images are attached.

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": {
      "view": "<view>",
      "x": "<x>",
      "y": "<y>"
    },
    "name": "zoom_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYesCentre of the close-up, pixels from the left of that view
yYesCentre of the close-up, pixels from the top of that view
sizeNoSide of the region in that view's pixels (default 200)
viewYesThe image ("1") or an earlier close-up ("1.2")

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.9.3

TDQS

A3.9/5.0
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 substantial work: it explains that each attachment is a numbered view, that the result is a nested child view ('1.1', '1.2') with its own pixel space, and that the close-up is drawn from the full-size original rather than upscaled. It leaves unstated whether the returned view is delivered as image data or a reference the agent must resolve, and nothing about invocation cost.

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 action and purpose, then the view model, then the chat-only constraint — a sensible order with no filler. A couple of sentences are cramped ('each is a view ("1") in the pixels you see') and take a re-read, but nothing is wasted.

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 four-parameter tool with no output schema and no annotations, the description covers what the tool produces, how nested views compose, and the environment restriction. The remaining gap is whether the new view's pixels are returned inline or merely referenced, which an agent would need to know to chain further zooms or point placement.

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 coverage is 100%, so x, y, size, and view are already documented, and the description mostly restates that points are 'in the pixels you see' for a given view. It does add genuinely non-schema meaning by explaining the view-labelling hierarchy ('Image 1' maps to view "1", close-ups to "1.2"), which is what an agent needs to pass the right string.

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 and resource: 'Look closer at an image the designer attached in the chat' and returns 'a close-up of the full-size original around a point.' The convergence of zoom semantics with the survey-map point-placement workflow makes the tool identifiable among the many garden/survey siblings, though no sibling is named as an alternative.

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?

Gives a clear trigger ('to place points precisely') plus an explicit boundary: 'Only in the editor's own chat, where images are attached.' It also routes downstream intent by noting points for set_survey_map and map_to_garden are given on any view; it stops short of stating when zooming is unnecessary.

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