Kits are coherent sets built to one palette and one grid. Reach for a kit when the user is building a whole environment rather than looking for one object. Each carries a status: "published" is finished and sold as a bundle, "filling-up" is still being built — and the parts of a filling-up kit are usable TODAY, they just are not sold together yet. Use get_kit to fetch the parts of either.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It adds useful context about kit statuses ('published' vs 'filling-up') and clarifies that filling-up kit parts are usable today, which helps the agent interpret results. However, it does not disclose the return format, pagination, read-only nature, or any other tool-specific behavior.
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 has four sentences, each contributing domain definition, usage guidance, status explanation, or an alternative tool. It is slightly longer than the minimal 'list kits' statement, but every sentence earns its place without being verbose.
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 zero-parameter list tool with no output schema, the description covers the key context: what kits are, when to use them, their statuses, and how to fetch parts. It does not explicitly state that the tool returns a list of kits with their statuses, but the name and context make that sufficiently clear.
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 input schema has zero parameters, so schema coverage is effectively 100%. No parameter description is needed, and the baseline of 4 applies.
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 clearly identifies kits as the resource and distinguishes this tool from get_kit, which fetches parts. However, it never explicitly states that list_kits lists all kits; the purpose is inferred from the tool name and the usage guidance rather than stated directly.
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 explicitly says when to reach for a kit ('building a whole environment rather than looking for one object') and points to an alternative ('Use get_kit to fetch the parts of either'). This gives clear context for when to invoke this tool versus related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct workflow: catalogue search, single-asset detail, kit listing/detail, variant generation, scene matching, terrain placement, preview, ownership, help, and feedback. Even the retrieval-heavy tools are separated by clear operation and output. An agent should be able to pick the right tool from descriptions alone.
All tool names are snake_case action phrases with consistent get_, list_, search_, find_, preview_, and report_ conventions. Retrieval tools uniformly start with get_ or list_, and the exceptions still follow a predictable action-first structure. There is no mixed casing or synonym soup.
At 11 tools the surface is well-scoped for a 3D asset catalogue and scene-building server. Each tool covers a distinct capability and none feels redundant or decorative. This is comfortably within the ideal range for a focused server.
The server covers the full discovery-to-scene workflow: search, inspect, kit composition, variant remixing, terrain placement, scene preview, and ownership checks. Missing catalogue entries and rough edges are explicitly handled by report_need, and get_help covers misuse, so there are no dead ends. No obvious domain operations appear absent for this server's stated purpose.
