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

Annotations cover the safety profile (non-readOnly, openWorld, non-idempotent, non-destructive), and the description adds the costly details they don't: this consumes external provider credits, each provider requires an integrations_set token first, and output is one freestanding object per task. The provider-capability matrix and the poll→import chain are exactly the context needed before invoking.

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 disambiguation and the authorization gate, then capabilities, then the follow-up workflow. Dense but every sentence carries operational information; nothing repeats the schema or annotations.

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 credit-consuming external generation call with three params and an output schema, the description covers cost, auth prerequisites, argument/provider compatibility, scope constraints, and the full downstream workflow. Nothing an agent needs to call it correctly is missing.

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 100%, so baseline is 3, but the description adds real semantics the schema lacks: which providers accept imageUrl versus prompt-only (hyper3d), and the constraint that prompt should describe a single freestanding asset. Provider-token requirements further constrain the enum values.

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?

Opens with a specific verb+resource ('Start a text/image → 3D generation') and immediately distinguishes itself from the catalog-search siblings ('External generation, not a catalog search'). An agent can tell it apart from assets_search and asset_import without opening any schema.

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?

Explicit gating condition ('start only when the user has chosen or already authorized this generation path'), an explicit prohibition ('Do not spend provider credits to discover candidate assets'), and named alternatives for the excluded cases (scene ops for ground planes/assemblies, duplicating for reuse). It also routes to the follow-up tools: asset_generate_status then asset_library_import.

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