transform_layer

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

With no annotations supplied, the description does real work: it discloses that the operation is bounded to a named layer, that the canvas is unaffected, that it mutates visible pixels, and that the default pivot is the layer center. It omits the order of scale/rotation composition and any failure behavior when the layer is missing, but the safety-relevant profile is clearly conveyed.

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?

Front-loaded with the action and scope, then unit conventions and the pivot default in short declarative sentences. The final clause about not inventing a camera view or revealing hidden surfaces reads as defensive boilerplate rather than useful tool information.

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 9-parameter mutation tool with no annotations and no output schema, the description covers units, pivot behavior and canvas scope but says nothing about what is returned, whether the transform is applied destructively, or what scale_x/scale_y and image_index control. Adequate, but not complete for this 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 documents units for the highest-risk numerics: rotation in degrees, translation and pivot in image pixels, and the default pivot of layer center. Two parameters (scale_x/scale_y defaults, image_index) go unmentioned, which is a real gap, but the unit/default disclosure it does provide is well beyond what the bare schema offers.

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 ('Apply a bounded, named-layer 2D transform') plus the key scope constraint ('without changing the canvas'). This implicitly separates it from canvas-level siblings like resize_canvas, rotate_image, and scale_image, though none are named explicitly.

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: the phrase 'without changing the canvas' signals this is the layer-scoped option rather than the image-scoped one. There is no explicit when-to-use/when-not guidance and no named alternative, so the agent must infer the routing from the scope wording.

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