Creative Lab — Make a Product (end-to-end)

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

Annotations cover the safety profile (non-readonly, non-idempotent, non-destructive), and the description adds much more: the call blocks for 2–5 minutes per stage with progress, returns only the final model, never surfaces the concept image, refunds FAILED stages, and charges still-running stages after timeout. The multicolor handoff constraint (task id not accepted) is a genuinely useful operational disclosure.

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?

Front-loaded with the one-line purpose, then organized into scannable labeled sections (Products and cost, Outputs, Examples). It is long, but for a 14-parameter tool with nine product variants and an internal multi-stage pipeline, nearly every line carries load; only the outputs paragraph is borderline 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?

There is no output schema, so the description carries the return-value burden itself by enumerating output artifacts per product (GLB, lamp_stl/base_stl, 3MF, STL+GLB) and naming the download path. Combined with timeout semantics and the multicolor follow-on, an agent has everything needed to call and chain this 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?

Schema description coverage is 100%, so the baseline is 3, but the description goes further by attaching credit costs to each product enum value and clarifying product-specific parameter scoping (name_text keychain-only ≤10 chars, base_model keycap-only, pixel_subject required for fidget-pixel). The worked examples also demonstrate non-obvious parameter combinations.

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?

States a specific verb and resource — 'Turn a photo into a finished Creative Lab product 3D model, end to end' — and immediately establishes scope (photo input only, no text prompt). The product enum list with per-product descriptions makes its distinctness from generic siblings like meshy_image_to_3d obvious to an agent.

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?

Gives strong routing guidance: 'confirm before calling' on cost, pass the reported task_type to meshy_download_model, and use meshy_process_multicolor with the GLB URL (explicitly noting the task id is not accepted). It does not, however, explicitly compare itself against the alternative generation tools (meshy_image_to_3d etc.), leaving the 'why this over that' inference to the agent.

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