paint_model

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

Annotations already establish it is a non-read-only but non-destructive, idempotent, closed-world operation. The description adds genuine behavior beyond that: rules are evaluated in order with 'later wins', z is measured from the part's base, and it returns a result plus a preview image that should be visually checked before trusting the paint. It does not mention auth, rate limits, or what exactly gets written, but the added semantics are substantial.

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?

Well front-loaded: a single-line purpose sentence precedes the rule grammar. The five JSON examples are dense but each demonstrates a distinct rule type, so they mostly earn their place; the block is longer than strictly necessary for a terse definition but proportionate to the tool's complexity.

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 13-parameter tool with 0% schema coverage and no output schema, the description covers the rule grammar and the return value (result + preview image) but leaves most parameters undefined, so an agent cannot know what path, printer, output_dir, filaments, or settings expect. Adequate on the core mechanic, incomplete on the surrounding configuration surface.

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 carries the full burden. It does an excellent job on the hardest parameter, 'rules' (five rule-type examples plus shared 'within' and 'only_from' keys), but the other twelve parameters (path, output_dir, printer, filaments, settings, resolution, object_type, base, name, slice, nozzle, process) receive no explanation at all. Valuable but partial compensation for a large coverage 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?

The description names a specific verb and resource ('Colour a single mesh by rules ... then slice and verify'), which is concrete and unambiguous. It distinguishes itself functionally from pure slicing siblings like slice_model by emphasizing the painting step, though it never names or explicitly contrasts any sibling.

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 only implicitly conveyed: you call it when you want to apply filament rules to a mesh and get a sliced, verified result. There is no explicit when-to-use/when-not-to-use guidance and no routing to alternatives such as slice_model or analyze_model, leaving the agent to infer the boundary.

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