Slice a PNG into parts for rigging

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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states that it writes part files and a base.png, mentions that base.png has parts erased, and says it returns bounding boxes for placement. Missing details like overwrite behavior and failure modes leave room for improvement, but the core side effects are well covered.

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 description is two sentences with no filler. The first sentence states the action and purpose, and the second explains outputs and integration. Every phrase adds value, and the structure front-loads the core purpose.

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 tool with no annotations, no output schema, and three parameters including a nested 'regions' array, the description does a solid job covering inputs, outputs, and return value. It could mention prerequisites (e.g., valid PNG, non-overlapping polygons) or error conditions, but it already conveys what the tool does, what it produces, and how it integrates with riv_create.

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 schema already documents most parameters (pngPath, outDir, polygon, keepInBase). The description adds meaningful semantics by explaining that the 'name' field becomes the filename for each part (<name>.png) and that output is meant for riv_create. This goes beyond the schema's bare property definitions, especially for the 'name' parameter which has no schema 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?

The description uses specific verbs ('Cut polygon regions') and identifies the resource ('character PNG') and purpose ('parts-based rigging (cutout animation)'). It clearly distinguishes itself from the sibling tool riv_create by explaining how the output is consumed ('Use with riv_create: images per part + groups as pivots').

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 description gives clear usage context by explicitly recommending pairing with riv_create. It doesn't specify when not to use this tool or alternative slicing approaches, but the 'Use with riv_create' workflow provides strong guidance about the intended role in a rigging pipeline.

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