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

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing the billing model (30 credits per new build, repeats and failures not charged), the runtime (1–6 min), and the async contract (may return a task_id for get_task). The billing-consent requirement is exactly the kind of behavioral context annotations cannot express, and it is consistent with idempotentHint=false since each build creates a new version.

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-loads what is produced, then price/consent, then runtime and async behavior — a logical order with no filler. The first sentence is long and clause-heavy, which slightly hurts scannability, but every clause carries real information.

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?

Covers cost, consent, expected duration, the async escape hatch, and what the user ends up with (a new version in the 3D viewer). With no output schema, the description still tells the agent what the result looks like, leaving nothing an agent needs missing before calling.

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 schema already documents texture size, triangle target range and wait_seconds. The description reinforces the meaning of two of them ('closed triangle mesh at a triangle target with the textures baked on') but adds no syntax, rounding or interaction detail beyond the schema, so the baseline applies.

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 ('Make a clean Low Poly version of one of the user's models') plus the concrete outcome: closed triangle mesh at a triangle target, textures baked, saved as a new version, shown in the 3D viewer. That is enough to distinguish it from generative siblings like generate_from_text or make_craft without opening a 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?

Gives clear context for use (game, AR and web assets) and an explicit pre-call procedure: quote the 30-credit price and get the user's OK first, plus how to follow up via get_task when a task_id comes back. It stops short of naming an explicit when-not or naming a competing sibling such as make_craft, so it is strong but not fully routing.

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