Create Design

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

Annotations indicate it is not read-only and not destructive, so the description adds value by noting that it generates and executes one script for the whole composition. This provides efficiency context. However, it does not detail side effects like whether it opens a new document or handles errors.

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?

The description is four sentences, each serving a purpose: stating the action, listing components, explaining execution, and giving use cases. It is front-loaded and contains no unnecessary words.

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?

Given the complexity (nested params, no output schema), the description covers the main function and use cases. It does not address error handling, prerequisites, or return value format, but these are partially clarified by context. Reasonably complete for a high-level tool.

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 coverage is 100% and the schema already describes each parameter with nested properties. The description summarizes the parameter categories but does not add new semantic details beyond what the schema provides.

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?

The description clearly identifies the tool as a high-level workflow that creates an entire design in a single call, specifying preset, background, layers, and guides. It distinguishes itself from siblings like ps_create_layer or ps_create_document by being a composite, all-in-one operation.

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?

The description mentions ideal use cases (social media posts, thumbnails, print layouts) but does not explicitly state when to prefer this over individual layer creation tools. The guidance is implicit through the 'high-level' and 'single call' phrasing, but lacks explicit exclusions.

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