build_name_backing

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so safety is covered. The description adds genuinely non-obvious behaviour: face holes are preserved, face and backing remain separate objects, and 'visual review is still required' warns the agent that output may not look correct. It still omits whether the source face is modified or what the tool returns.

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?

Three dense sentences, front-loaded with the operation and followed by the two actionable caveats. No filler; the only mild dilution is the middle sentence, which could be merged into the parameter clause.

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?

No output schema and no annotation-level detail on mutation semantics, so the description must be self-sufficient. It covers behaviour well but leaves a 4-required-parameter, nested-object schema largely opaque, which is thin for a destructive compound operation.

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 carries the full load. It meaningfully explains the gradient_name-vs-stops fork and that bounds/thickness (offset_pt) are in native document points, but document_path, root_layer_path, face_name, backing_name and angle get no explanation at all.

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 compound verb+resource: duplicate a name face, apply a gradient, attach an Offset Path effect. An agent can tell it apart from generic siblings like duplicate_objects or duplicate_layer_tree. It stops short of explicitly naming which sibling to prefer when the goal is simpler.

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?

There is no when-to-use or when-not-to-use guidance and no named alternative (create_gradient, duplicate_objects, apply_graphic_style are all plausible neighbours). The only routing hint is the implicit 'template gradient or explicit RGB stops' fork, which is about parameters, not tool selection.

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