Generate 3D Model from Multiple Images

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

Annotations only declare safety flags (not read-only, non-idempotent, open-world, non-destructive); the description goes far beyond by disclosing the credit cost formula per model and per add-on, that texturing is on by default, and that input_task_id must reference a SUCCEEDED task. It also actively warns about deprecated parameters that the schema still exposes, which an agent would otherwise misuse.

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 core purpose and cost, then organized into labeled blocks (IMAGE INPUT, model selection, a worked example). It is long, and a few lines restate what the schema already annotates, but for a 30-parameter tool with an enum-heavy matrix the density is largely justified.

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 30-parameter generation tool, the definition covers input modalities, cost, model-combination rules, defaults, deprecations, and a concrete end-to-end example. An output schema exists and annotations carry the safety profile, so the remaining burden on the description is fully discharged.

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 coverage is already 100%, so the baseline is 3, but the description earns more by mapping model choices to project intent (e.g. meshy-t2.5 + meshy-n1 for a riggable character) and translating options into plain terms ('"none" is should_texture false', 'omit texture_model for the geometry's default'). It does repeat some schema-level detail (file_paths vs image_urls) rather than adding to it, and mutual-exclusion rules between texture_image_urls / texture_prompt are only partly restated.

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 ('Generate a 3D model') plus the distinctive scope ('from 1–4 views of the same object'), and notes the default texturing behavior. That scope immediately separates it from the single-image sibling meshy_image_to_3d and from meshy_text_to_3d.

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 an explicit input contract ('IMAGE INPUT (exactly ONE)') and a project-to-model mapping table (hero asset, game character, props, real object from photos, 3D print, cheap drafts) with concrete parameter pairings. It also flags a cross-tool constraint ('smart topology is meshy_image_to_3d only'). What it never states outright is the boundary case: when a single photo should route to meshy_image_to_3d instead.

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