ps_newDocument

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description adds the useful fact that dimensions are in pixels. Beyond that it says nothing about what happens to the currently open document, whether the new document becomes active, or what the defaults are for the five optional parameters. Adequate, but not rich.

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 front-loaded clause names the action and units, followed by a compact parameter rundown with no filler. The dash-list style is dense and slightly telegraphic, but every element maps to something the caller needs to know.

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?

With seven parameters, five of them optional and no output schema, the definition should tell the agent what happens when optional fields are omitted and what a successful call returns or activates. It covers the parameter surface but leaves defaults and post-call state unspecified, so it is workable rather than complete.

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 0%, so the description carries the burden, and it does enumerate all seven parameters including the enum value sets — but those enums are already in the schema, so that text only repeats structured data. It does not supply defaults (resolution, mode, fill, bits), the unit for resolution (ppi vs px), or valid ranges for width/height, which is exactly the missing information.

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+resource ('create a new document') qualified by the 'Photoshop:' application prefix, which separates it from ai_newDocument, ae_newProject and pr_newProject in the sibling list. It also enumerates the settings the document is created with, so an agent knows exactly what the call produces. No explicit sibling callout, but the app prefix does the differentiation work.

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?

Use is implied by the name and by the fact that it is the Photoshop document-creation entry point, but the description never says when to prefer it over ps_openFile or ps_placeFile, nor states prerequisites such as Photoshop having to be running or a document becoming active. An agent can infer intent but not the conditions.

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