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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description earns extra credit by disclosing that existing files are never overwritten, a new folder is created, and that it returns paths, validation, and the actual preview image. This is meaningful behavioral context beyond the annotations.

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 outputs and the key constraint (new folder, no overwrite). A few dense sentences, mostly earning their place. Slightly terse on some nested semantics but no filler.

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 exists, but the description explains return values (paths, validation, preview image) and the no-overwrite behavior. Combined with the nested Paint/Design schema, an agent has enough to call it correctly, though model/layer/palette details rely on the schema.

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 reported at 0%, but the $defs carry inline descriptions (rect as [x,y,w,h] face-local texels, color as existing palette key). The description adds meaning ('All six base parts require opaque palette colors', 'Paint is ordered rectangles within a face'), which compensates partially, but name, model, layer, and palette format remain undocumented in the description.

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 (build) and enumerates concrete outputs: 64x64 PNG, editable design.json, and front/back/side previews in a new named folder. This clearly distinguishes it from siblings like skin_validate, skin_preview, and skin_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 useful usage constraint ('Use a new name for each revision; existing files are never overwritten'), which implies versioning workflow. However, it never explicitly contrasts with siblings (e.g., use skin_validate before building, or skin_preview to inspect), leaving the when-to-choose-this decision implied.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavior detail: the result is a four-view orthographic inspection sheet, outer layers composite at native texel scale, and it is not a 3D rendering. It does not describe error behavior for invalid paths.

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?

Two compact sentences with no wasted language. The output shape is front-loaded, and the scale/rendering clarification follows immediately.

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?

The description covers the output artifact well enough for a read-only inspection tool with no output schema. However, it leaves gaps about path format (relative vs. absolute, extension expectations) and does not explain the model 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 description coverage is 0%, so the description must compensate for both parameters. It partially documents 'path' by saying the PNG must be inside the output root, but it never mentions the 'model' parameter or the classic/slim distinction, leaving a key enum undocumented in prose.

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 states a specific verb and resource: returning front/back/right/left orthographic images of a PNG inside the output root. It also clarifies the artifact type ('inspection sheet, not an in-game 3D rendering'), which cleanly separates it from siblings like skin_build and skin_validate.

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 implied by 'inspection sheet' and 'inside the output root', but there is no explicit guidance on when to choose this over skin_validate or other siblings. The exclusion of 'in-game 3D rendering' clarifies scope, not when to use an alternative tool.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful output semantics about faces being viewed externally and the local top edge conventions for top/bottom faces, which is meaningful context beyond annotations.

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?

The purpose is front-loaded in the first sentence, followed by compact orientation clarifications. Each sentence adds either purpose or coordinate semantics, with no redundant filler.

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, the description must convey return behavior; it names the returned artifacts and orientation conventions. However, it omits how the model parameter changes output and does not describe the design JSON structure, leaving a notable gap.

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?

The only parameter, model, has 0% schema description coverage; its enum values classic/slim are somewhat self-explanatory, but the description never mentions the parameter or explains how model affects the returned schema or UV sizes. It does not compensate for the documentation gap.

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 ('Return') and resources ('design JSON schema and canonical UV face sizes'), plus orientation semantics. It does not explicitly differentiate from siblings skin_build, skin_validate, or skin_preview, so it falls short of a 5.

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?

Provides no explicit when-to-use or when-not-to-use guidance, and never mentions the sibling tools. The purpose implies retrieval of schema/UV sizes, but the agent must infer when this tool is preferable to skin_build, skin_validate, or skin_preview.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the validation scope is limited to technical compatibility (not art quality or in-game acceptance) and the path is constrained to the output root. It omits what a failure result contains, which keeps it below 5.

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 short sentences, front-loaded with the action, then the key invocation constraint, then the boundary of the check. No filler and nothing repeated from the schema or annotations.

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 two-parameter read-only validator with no output schema, the description covers purpose, scope limits, and the model requirement well. The remaining omission is the shape of the result (pass/fail fields, error reporting), which matters somewhat because no output schema exists to document it.

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 must carry the load, and it does: it explains why `model` (classic/slim) must be provided explicitly and scopes `path` to the output root. It does not state the consequence of an incorrect model value or what an invalid path does, leaving a small gap.

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 object ("Validate a PNG inside the output root") and scopes the check to technical compatibility rather than artistic quality or in-game acceptance. Siblings (skin_schema, skin_build, skin_preview) are not named or differentiated, but the purpose is unambiguous on its own.

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 clear usage context: the model argument must be supplied correctly because the PNG alone cannot disambiguate classic/slim geometry, and explicitly bounds what the tool does not judge. It stops short of saying when to call it relative to skin_build or skin_preview, so it is clear context without explicit alternatives.

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