import_layer

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

With no annotations, the description carries the full burden; it usefully discloses that pixels/alpha and native dimensions are preserved, that no other image is opened, and what the call returns. It omits failure behavior (what happens if no image is open or the path is invalid), whether the import is undoable, and any path/permission constraints on file_path.

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?

Four short sentences with the core action and the key negative constraint front-loaded, and no filler. The list of returned fields is slightly redundant given the tool's simplicity but still earns its place as a return hint.

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 6-parameter mutation tool with no annotations and no output schema, the description covers the important conceptual behavior and the return shape but leaves error modes, the semantics of image_index and name, and edit safety unaddressed. Adequate as a minimum, incomplete for the tool's complexity.

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 0%, so the description must compensate, and it does for half the parameters: x/y are clarified as exact canvas pixel offsets and position as a top-to-bottom insertion index with 0 meaning top. file_path, name (including what null defaults to), and especially image_index are left undefined, and image_index is genuinely confusing against the "already open image" framing.

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 and resource ("Import an existing local asset as a layer") plus the target scope ("owned, already open image"), and explicitly distinguishes itself from open_image by saying it does not open another image. An agent can tell this apart from create_layer and open_image without opening any 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?

Gives a clear precondition (an image must already be open and owned) and rules out the adjacent alternative of opening a file as a new document. It stops short of naming create_layer/duplicate_layer as the alternatives for non-file sources, so the routing guidance is clear but not exhaustive.

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