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

Annotations only declare readOnly=false, destructive=false and openWorld=true; they say nothing about execution model. The description adds the crucial fact that this is asynchronous and returns a job id/status that must be polled via get_three_d — behavior not inferable from the annotations or schema.

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?

Two short sentences, zero padding: the capability comes first, the critical async/polling constraint second. Every clause earns its place and the most actionable fact (async + poll) is front-loaded in the flow.

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 10-parameter, nested-object, mutating generation tool with no output schema, the description covers the two things the schema cannot: the async job contract and the retrieval path. What remains thin is operation-specific dependency guidance (text-to-3d vs image-to-3d vs remesh/rig inputs), which is only implicitly covered by the schema.

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% and the schema is unusually rich (tier, model cancellation warning, params semantics, per-operation URLs), so the description rightly defers to it. It adds nothing beyond the schema for the 10 parameters, which is acceptable given full coverage but earns no extra credit.

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 asset/mesh) and names the companion tool get_three_d for retrieving the result, which lets an agent separate it from that poller. It does not, however, differentiate itself from the other generate_* siblings (generate_image, generate_video, generate_audio), so the agent gets no help on 3D vs 2D selection.

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 gives a strong post-invocation workflow ('returns a job with an id and status — poll get_three_d'), which is real routing guidance. But it offers no when-to-use guidance relative to the other generation tools, and no when-not-to-use or prerequisite conditions (e.g. when image_url or input_task_id is required per operation).

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