sweep

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the tool selects cheapest-first across NameWhisper, OpenSea, and Grails, packs into one transaction, caps at 20 names, skips orders that sold and refunds the excess, and reports the swept items and totals. This is rich, specific behavioral context beyond just 'sweep'.

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?

The description is front-loaded with a one-sentence definition, then moves to usage guidance, parameter explanation, and execution/response details. Every sentence is substantive with no fluff or repetition. The structure is logical and easy to scan.

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 tool with 9 parameters, no annotations, and no output schema, the description is remarkably complete. It explains how to configure the sweep, the marketplaces used, the transaction packing, the cap and continuation, the refund behavior, and the exact contents of the response (marketplace + price, total, and out-of-bound count). This is enough for an agent to know when and how to invoke it correctly.

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?

Although the schema descriptions cover each parameter individually, the description adds meaningful synthesis by grouping parameters into cohort filters (category, q, charType, minLength, maxLength) and bounds (count, maxBudgetEth, maxPriceEth). It explains how count and maxBudgetEth interact, the count default, and the 20-name cap. This cross-parameter guidance is valuable beyond the schema.

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?

The description clearly states what the tool does: buys the cheapest N listed ENS names in a category or matching a filter, in one Seaport transaction. It distinguishes itself from the batch_purchase tool by explicitly contrasting 'cheapest N' vs. naming specific names, and references the sibling tool by name.

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?

Provides explicit when-to-use guidance: 'Use this when the user wants "the cheapest N", "sweep the floor", or "buy up to X ETH of" a cohort' and explicitly names the alternative (batch_purchase) for specific-name purchases. It also walks through how to select a cohort and bound the sweep, giving clear context for when this tool is appropriate.

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