ai_addShape

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

Annotations already declare non-read-only, non-destructive, closed-world, so the mutation profile is known. The description adds genuine behavioral detail beyond that (position is the top-left of the shape in artboard coordinates, fill/stroke accept hex or the literal "none"), but is silent on whether the new item is selected, whether a missing layer is created, and what is returned (no output schema).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with zero filler; every token maps to a shape type or parameter. It is front-loaded with the verb and resource, though the comma-chain of options is harder to scan than a short structured list would be.

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

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

For a 14-parameter creation tool with 7% schema coverage and no output schema, the description leaves real gaps: per-shape parameter requirements, the meaning of sides/closed/cornerRadius, and what the call returns. It covers the common case well but not the full call surface.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 7% across 14 params, so the description must carry the load and mostly does: points format [[x,y],...], position [x,y], size [w,h], hex-or-none fill/stroke, strokeWidth, opacity, name, layer are all explained. It omits sides, closed, and cornerRadius, and does not say which parameters are required per shape (points for path, sides for polygon/star).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('draw') plus the full resource set (rect, roundedRect, ellipse, polygon, star, line, path) and the host app (Illustrator). An agent can distinguish this from ai_addText, ai_modifyItems, or ae_addShapeLayer without opening the schema.

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

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

Usage is only implied: 'artboard coords' and the shape enum tell the agent this draws new vector geometry in Illustrator, but there is no explicit when-to-use, when-not-to-use, or pointer to siblings such as ai_modifyItems for editing existing shapes. No prerequisites (open document, active artboard) are stated.

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