list_design_templates

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes beyond that by disclosing that rendering happens locally via OpenSCAD, requires no AI provider or API key, and is free — operationally relevant facts absent from structured fields. It also enumerates what each returned record contains (parameters with defaults/units/descriptions, pre-validated OpenSCAD, category and job description), which compensates for the missing output schema.

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?

Purpose is front-loaded in the first sentence, the bulk is a scannable bulleted list of what a template record contains, and the routing advice sits at the end where an agent looks for next steps. The emphasis on 'FREE and need no AI provider or API key' earns its place because it tells the agent this path avoids a paid generation dependency.

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 input parameters and no output schema, the description carries the full burden of explaining the return shape, and it does so item by item. Combined with the annotations covering safety and the explicit routing to find_design_templates and generate_from_template, an agent has everything needed to select and use it correctly.

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?

This tool takes zero parameters, so the baseline is 4; the schema is empty and there is nothing to disambiguate. The description does explain the parameter shape of the sibling calls it routes to (use_case for find_design_templates, template_id plus a parameter object for generate_from_template), which is a small bonus but not required here.

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 opens with a specific verb and resource ('List every parametric part Kiln can build, with full parameters') and immediately characterizes what those templates are: print-verified functional parts rendered locally through OpenSCAD. That framing separates it from the sibling find_design_templates, which searches rather than enumerates.

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?

It gives an explicit use condition ('Whenever a user wants a functional part to their own dimensions, check here before writing OpenSCAD from scratch') and names the preferred alternative with the exact condition that selects it ('Prefer find_design_templates(use_case) when you know what the user is making'). It also names the follow-on tool, generate_from_template(template_id, {...}), so the whole call chain is spelled out.

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