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

The description discloses key behaviors beyond annotations: it returns a job handle (async), explains source-specific transformations (HDRI becomes world environment, texture sets become wired PBR material), and mentions scaling. It also notes the token requirement for Sketchfab. These are valuable details not captured by annotations. It does not contradict the annotations (readOnlyHint false, openWorldHint true, etc.).

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 is dense but well-structured, starting with the core purpose and then using clear 'source=' segments to organize source-specific details. Each clause carries necessary information, and the front-loaded main sentence gives immediate context. It is appropriately sized for the 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?

Given the tool's complexity (10 parameters, multiple sources, async job handle) and the presence of an output schema, the description covers the essential behaviors: revision creation, job handle, per-source semantics, token requirement, and scaling guidance. It also ties into asset_generate_3d for generation tasks. The description is thorough and leaves little ambiguous for an agent to call 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?

With schema description coverage only at 30%, the description adds substantial meaning for parameters like slug (explaining what it means per source), source (enum meaning), targetSize (with real-world examples), and applyToObjects (assignment behavior). This significantly compensates for the low schema coverage and helps agents understand parameter usage without opening the schema.

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 states the verb 'import', the resource 'library asset', and the outcome 'into a project as a new revision', plus it returns a job handle. It is specific enough to distinguish from the sibling 'asset_import' by focusing on library sources and revision semantics, even without naming the sibling explicitly.

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 provides clear context on how to use the tool across different sources (polyhaven, sketchfab, hyper3d/hunyuan3d/tripo3d), including source-specific requirements like the Sketchfab token and taskUuid from asset_generate_3d. It also explains scaling with targetSize. However, it does not explicitly state when not to use this tool versus the sibling 'asset_import', so it lacks a direct exclusion.

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