Rig a layered PSD into a new Spine project

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the substantive behavior: dry-run verification before any write, post-write validation plus rig QA and test-pose renders, and the explicit guarantee 'Never overwrites.' Those details materially change how an agent would sequence the call. It omits prerequisites (e.g., whether a Spine editor project must be open) and what the dry-run report contains.

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?

It is front-loaded and compressed to a few dense clauses with no filler sentences, and the mode-based structure is a sensible skeleton. But the telegraphic style (e.g. 'hidden lids rigged shut-collapsed', 'nothing written; riders: ...') crams unrelated ideas into semicolon chains, making it harder to parse than a slightly longer explicit form would be.

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 17-parameter, write-capable pipeline tool with no output schema and 12% schema coverage, the description covers workflow but not the parameter surface, the shape of the dry-run/QA results, or runtime prerequisites. The agent can grasp the intended flow but cannot confidently supply most arguments without trial and error.

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 only 12% across 17 parameters, so the description is required to compensate and largely does not. It explains the semantics of roughly five knobs (bones with joints/tips, mesh tracing, weights, two-bone ik, riders = one character sitting on another, rigFrom = an approved rig's joints) but leaves psd, parts, layout, skeleton, output, scale, origin, density, blend, targetHeight, and the apply flag undocumented. With two-thirds of the surface area undefined, an agent is left guessing on numerics and file inputs.

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 names a specific verb and resource — rigging a starting skeleton/project from a layered PSD or parts+layout — and enumerates concrete outputs (bones at joints, traced meshes, weights, optional two-bone IK). It cleanly splits the tool's two operating modes (no bones vs. with bones), which lets an agent tell the sub-behaviors apart. It never names the closest sibling (spine_rig_edit) for editing an existing rig, so sibling differentiation is implied rather than stated.

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?

The mode split is explicit guidance: with no bones supplied it only *suggests* a skeleton and writes nothing, and the result is meant to be passed back as bones; with bones supplied it dry-runs with checks first and only writes when apply is set. That is clear when-to-use framing for the tool internally. It gives no explicit exclusions relative to alternatives such as spine_rig_edit or spine_import_layers, so an agent must infer which tool to pick.

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