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

With destructiveHint=true and idempotentHint=true already declared, the description goes well beyond the annotations: it discloses the authorization constraint (bidder only), that the output is unsigned calldata rather than a broadcast transaction, the WETH-release consequence, and that batched cancels cost barely more than one. These are exactly the behavioral facts an agent needs before invoking a destructive tool.

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 short paragraphs, front-loaded with action and return value before the caveats. Every sentence carries information, though the WETH-release paragraph is slightly more elaborate than the calling decision strictly requires.

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, and the description compensates by describing the return ('unsigned Seaport cancel() calldata', result lists every cancelled order) plus the post-conditions. Combined with auth requirements and sibling routing, an agent has everything needed to call this 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains WHY alsoCancel exists (the signed 'opensea' variant of a cross-posted offer), restates the 8-item cap and the do-not-repeat-orderHash rule as operational advice, and ties all alsoCancel entries to the same name. It largely duplicates schema text, which keeps it short of a 5.

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 ('Cancel an active offer ... on an ENS name') and immediately names the return artifact ('unsigned Seaport cancel() calldata'). It explicitly separates itself from cancel_listing and from collection-offer cancellation, so differentiation from siblings is settled in the first and last sentences.

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 explicit when-to-use ('Only the bidder ... can cancel'), an alternative for the adjacent case ('For cancelling your own listings, use cancel_listing'), and routes collection offers off-tool. The cross-posted OpenSea scenario explains exactly when the alsoCancel path applies.

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