ps_smartObject

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

The parenthetical '(opens it)' is genuinely useful side-effect disclosure for the edit action, and 'replace contents with a file' hints at an external file dependency. However, the description never warns that rasterize is irreversible and discards smart-object data, which sits awkwardly against destructiveHint=false and leaves the one truly lossy action unexplained.

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 sentence with the resource first and the operations after; every clause corresponds to a real enum value and nothing is redundant. The comma-separated run-on is slightly harder to scan than a short 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?

With no output schema and no annotations explaining returns, the description should say at least what 'edit' or 'export' produce (e.g., an opened document, a written file). The per-action parameter requirements are also unstated, which is the main practical gap for a multi-action tool with one required parameter.

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 50%: `layer` and `document` are already documented in the schema, and `action` is a self-describing enum. The description does add meaning to the undescribed `path` by tying it to file-based replace/export, but it omits the critical per-action mapping of which parameters are required.

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 names a specific resource (Photoshop smart objects) and enumerates the five operations that map one-to-one onto the `action` enum (convert, edit, replace, export, rasterize), so an agent can predict the call shape immediately. It stops short of distinguishing this from adjacent layer-manipulation siblings such as ps_layerOps, but the smart-object scope is distinctive enough.

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 by the action list; there is no statement of when to pick this over ps_layerOps or ps_placeFile, and no note that 'replace'/'export' require a file path while 'convert'/'rasterize' do not. 'edit contents (opens it)' is the one piece of situational context provided.

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