baker_skew_preview

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

Goes beyond the annotations (readOnlyHint=false, destructiveHint=false) by clarifying that 'nothing is written into the scene' even though low materials are visibly repainted, and by naming the restoration tool. It stops short of saying whether the preview persists across scene operations or how mask_size affects cost, so not a full 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?

Front-loaded with the operation and its visual result, then the rule details, then the workflow. Dense but each clause carries information; the parenthetical 'black = averaged cage, white = corrected' is the only line whose payoff for tool selection is unclear.

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 an 8-parameter, zero-coverage tool with an output schema, the description covers behavior, side effects, and the surrounding workflow well enough to call it correctly. The gap is the unexplained baker/groups scoping parameters — an agent cannot tell from this text which bakers or groups the preview applies to.

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?

With 0% schema description coverage, the description carries the burden and mostly does: it defines seam_px/hard_px/bend_px as band widths in bake pixels, explains that 0 disables a band, gives bend_deg its threshold meaning, and describes soft_px as a falloff. It leaves baker, groups, and mask_size completely unexplained, which holds it below 5.

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?

Names a specific operation (compute skew masks by edge rule) and its visible effect (base colour on the low materials), so the agent knows exactly what happens. It also distinguishes itself from the two closest siblings by naming baker_skew_apply and baker_skew_clear_preview as the follow-up and undo paths.

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?

States the workflow explicitly: 'check the look, adjust, then baker_skew_apply', and gives the exit path via baker_skew_clear_preview. The condition selecting this tool over the apply variant (non-destructive preview) is spelled out rather than implied.

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