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

Goes well beyond the annotations: rejects calls with neither prompt nor image (HTTP 400) and images over 15MB, holds credits on acceptance and refunds on failure/cancellation, costs 0.5 credits, and explicitly declares the async contract (returns {id, status}, poll getApiJob). The request_id dedup note is not a contradiction of idempotentHint=false — the default call is non-idempotent and only request_id opts into reuse — but the description makes that distinction clear.

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 purpose then usage, and nearly every sentence carries operational value (the 15MB/400 limits, the credit hold, the async return shape). It is dense and reads as one long run-on block, so a small amount of structural splitting would help, but there is no filler to cut.

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?

No output schema exists, yet the description still states the return contract ({id, status}, single image result with a url, not an array) and the polling path. For a one-parameter nested async job tool, an agent has everything needed to call it, poll it, and chain the result.

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 the baseline would be 3, but the description adds semantics the schema does not: the prompt's meaning flips depending on whether an image is supplied, and leaving it out preserves the character as-is. The credit/request_id retrieval behavior is reinforced rather than newly explained.

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+resource ("make a character image ready to turn into a 3D model") and positions it as the first step of Directional Sprites, distinguishing it from createImage/editImage and from the downstream create3DModel. An agent can tell what it produces and where it sits in the pipeline without opening the 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 branch logic: prompt only (describes a new character), image only (redraw) or both (prompt becomes edits); omitting the prompt keeps the character unchanged. It also names the downstream consumer (pass the returned url to create3DModel), the retry path (call again for another try), and the retrieval path (listGenerations type image via request_id).

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