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

With no annotations at all, the description carries the full burden and does so: it states the transaction is never signed or sent, that on-chain status and deadlines are validated against the latest block before proceeding, that the signing wallet must be the buyer wallet that funded the order, and that on escrow v3 funds are credited rather than transferred. Those are the safety, precondition and auth facts an agent would otherwise have to guess.

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 the scope constraint ('never sign or send') and packed into four dense sentences with no filler. The parenthetical qualifiers are efficient, though the sentence listing four actions at once is a little heavy to parse.

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 four-parameter mutation-preparation tool with no annotations and no output schema it covers the important parts: preconditions, wallet auth, cross-tool follow-up. What it omits is what 'prepare' actually hands back (an unsigned transaction for the wallet) and any guidance on chainId, which an agent must still resolve elsewhere.

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 only 25%, so the description must compensate — and it does well for 'action', explaining the semantics of all four enum values far beyond the bare enum, and it touches escrow v3 behaviour relevant to escrowVersion (whose schema description already covers the default rule). However 'chainId' and 'orderId' get no treatment at all, leaving a genuine gap for a low-coverage 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?

Names a specific verb ('prepare' — explicitly not sign or send) and resource (an order follow-up transaction), then enumerates the four action variants with their trigger conditions. It is immediately distinguishable from siblings like prepare_withdraw and accept_proposal, which are either named or clearly outside the enumerated set.

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 an explicit condition per action: approve_delivery '(after verifying the deliverable)', claim_timeout_refund '(seller missed the deadline)', claim_dispute_timeout '(escrow v3: the arbitrator did not rule within 14 days)'. It also routes the agent onward to prepare_withdraw for the v3 credit case, so the handoff between siblings is spelled out rather than inferred.

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