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

With no annotations provided, the description carries the full behavioral burden and handles it well: it discloses that the tool verifies ownership and transferability, injects the interface fee server-side, returns a one-time NFT approval and EIP-712 data for the user to sign, and explicitly states 'Never signs or holds keys.' This makes the side-effect profile and trust boundary 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?

Four dense sentences with zero filler. The first sentence states the purpose, the second covers behavior and output, the third handles the key conditional parameter rule, and the last clarifies the trust boundary. Every sentence earns its place.

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 complex 10-parameter tool with no output schema, the description covers purpose, preconditions, process, return value, and conditional name-market behavior—all essential for correct invocation. It is missing only an explicit routing note against sibling prepare_* tools and a prose explanation of marketId, which would make it fully self-contained.

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 60%, so the description must add conditional meaning, and it does: 'Name markets (basenames) take `name` instead of tokenId' clarifies the most important parameter relationship. It also frames `kind` via SELL listing vs. Dutch auction. It does not define `marketId` or `seller` in prose, but those remain clearer from the schema's required fields.

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?

Description states a specific verb and resource: 'Prepare a SELL listing or Dutch auction.' It goes further by naming the distinct action modes (listing vs. dutch_auction), the verification steps, and the returned artifact (NFT approval + EIP-712 typed data), which clearly differentiates it from sibling prepare_* tools such as prepare_offer, prepare_purchase, and prepare_cancel.

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 clear context: this tool is for sellers creating a listing or Dutch auction, and it includes the ownership/transferability prerequisite. It does not explicitly say 'use prepare_offer for offers' or 'use prepare_purchase for buying,' so it stops just short of naming alternatives, but the SELL framing and sibling context make the intended use evident.

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