Skip to main content
Glama
lazyq666

Illustrator MCP Unified

by lazyq666

Create Rectangle

create_rectangle

Draw rectangles in Illustrator at specified coordinates and size, with optional fill, stroke, corner radius, and layer. Runs in background without activating the app.

Instructions

Create a rectangle. Runs without activating Illustrator in default background mode; never invokes Computer Use.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xYesTop-left X coordinate
yYesTop-left Y coordinate
fillNoFill color
nameNoObject name
widthYesWidth
heightYesHeight
strokeNoStroke settings
layer_nameNoTarget layer name
corner_radiusNoCorner radius
coordinate_systemNoCoordinate system. Auto-detected from document by default (CMYK/print → document, RGB/web → artboard-web). artboard-web: origin at active artboard top-left, Y-down. document: Illustrator native coords, origin at bottom-left, Y-up. Call get_document_info to check which system is active.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0-local.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description does add genuinely new context by disclosing the non-activating background execution path and that Computer Use is never invoked, but it says nothing about the resulting object's state (selection, layer placement) or failure behavior.

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?

Two short, front-loaded sentences with no filler; the purpose leads and the execution-mode caveat follows. The second sentence is somewhat narrow in focus but does earn its place as non-obvious behavior.

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?

For a 10-parameter mutation tool with nested fill/stroke objects and no output schema, the description is thin: it omits defaults (corner_radius=0), layer targeting behavior, and what is returned or selected after creation. The very rich schema and existing annotations compensate substantially, keeping this at a minimum-viable 3.

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%, including a rich explanation of coordinate_system and the nested fill/stroke color variants, so the schema carries the parameter burden. The description adds no parameter-level meaning beyond that baseline, so a 3 is appropriate.

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 description states a specific verb+resource ('Create a rectangle'), which is unambiguous. However, it offers no differentiation from the numerous sibling creation tools (create_ellipse, create_line, create_path, create_text_frame), so the agent must rely on the name alone to choose among them.

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?

There is no when-to-use guidance, no preconditions (e.g., a document must be open, a target layer must exist), and no mention of alternatives. The only contextual sentence concerns execution mode, not selection between tools.

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