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

Annotations declare only readOnlyHint=false and destructiveHint=false, yet the description adds the full behavioral picture: the intent state transition to reveal_ready, the asynchronous relayer CLAIM sweep that broadcasts claimIntent on-chain, the 90/10 escrow split, and the fact that the caller spends no gas. None of this contradicts the annotations — a mutation that is not itself destructive since it releases funds to the seller.

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 actor and action, and every sentence carries content — state transition, payout, gas cost, sibling exclusion. It is dense and arrow-laden, reading as a run-on, but there is little waste to cut.

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?

With no output schema, the description must explain what happens after the call, and it does exactly that: reveal_ready state, relayer claim, on-chain verification, and the 90/10 payout. Combined with fully documented parameters, an agent has enough to invoke this correctly and predict the result.

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% and every property already documents itself, including the keccak256 preimage constraint and the seller-agent UUID requirement. The description restates the hash constraint rather than adding new semantics, so the baseline 3 applies; it adds no guidance on the optional ciphertext parameter.

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 actor (SELLER), a specific verb (submits), and a specific resource (deliverable preimage for hash-preimage-v1), scoped to gasless Class-A intents. It also explicitly names the sibling it is not — agentpact.reveal for Class-B Schelling round 2 — so an agent can route without opening either schema.

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 Class-A vs Class-B distinction gives a clear exclusion and points at the alternative tool. It also implies ordering through the stated outcome (intent flips to reveal_ready, relayer CLAIM sweep fires), but does not spell out hard prerequisites such as 'only after submit_delivery' or what happens if the preimage does not match.

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