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

The annotations already declare readOnlyHint=true and idempotentHint=true, and the description is consistent with them: it explicitly returns an *unsigned* transaction rather than sending one, and says the commit is simulated from the supplied wallet. Beyond that it discloses the receipt check against the chain's matcherSigner and where the kit's values are read from (the chain), which annotations cannot convey. It does not say what a failed simulation or a mismatched signer yields.

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?

It is front-loaded around the two modes, but the kit inventory is delivered as a single long parenthetical of eight comma-separated items, and the sentences run on. The final warning sentence earns its place; the enumeration of kit fields could be tightened into a list without losing substance.

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?

There is no output schema, so the description must describe what comes back, and it does cover both return shapes (kit contents, and a simulated unsigned commit transaction). Combined with the receipt-binding warning, that is close to everything an agent needs to call this safely; only error/failure behavior is unaddressed.

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 still adds real meaning: `builder` is explained as turning a Bookrunner code into the bytes32 an order carries, `wallet` is scoped to the sending owner or its session key and only relevant with a receipt, and `receipt` is characterized as binding a commitment rather than visible terms. The nested `{ owner, market, commitment, deadline, signature }` shape is left to 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 states two concrete modes: without a receipt it returns an 'order kit' (Zero Dark address, matcher sealing key, receipt signer, lot size, caps, next/last auctions, encoding, command), and with a receipt plus wallet it returns 'the unsigned commit transaction, simulated from that wallet'. That is a specific verb-plus-resource picture, though the naming ('order kit, then the commit transaction') alone would be opaque without the body text.

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?

It gives an explicit branch: call with only `market`/`builder` when you need the kit, add `receipt` and `wallet` to get a commit transaction. It even carries a warning about whose receipt to commit ('a receipt someone else hands you commits whatever order they sealed'). It never names the sibling tools (darkroom_orders, darkroom_cancel, darkroom_markets) as alternatives, so routing relies on inference.

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