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

Rich context beyond the annotations: free/no gas, signature equals consent to token payment, house never holds a key, and the returned MESSAGE_TO_SIGN must be signed then submitted within 5 minutes. Minor tension: the text says the board 'writes the same settlement record' while readOnlyHint=true is technically right only because the actual write happens in submit_token_settlement — an agent could misread this call as the write.

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 key inputs and prerequisites are front-loaded, but the prose is a dense run-on and the cost/signer guidance is stated twice ('FREE, no gas' then 'Cost and signer: free, no gas'). Several clauses (place standing, board settled count) are background rather than actionable.

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 two-step sign-then-submit flow with a documented output schema, the description supplies the missing operational context: what comes back (MESSAGE_TO_SIGN, BODY_JSON), how to sign it, which wallet signs, and the 5-minute deadline. Nothing an agent needs to invoke it correctly is absent.

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 parameter (txHash, workId, chainId, workerWallet) is already documented there, including the chain enum. The description reinforces that workerWallet must be the wallet on the approved proof and will be the signer, but adds little syntax/format detail beyond the schema, so the baseline 3 applies.

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 action (prepare the record that a token payment settled a proved packet) with the exact inputs (chain id, tx hash) and names the paired submit_token_settlement step. It also carves itself away from prepare_direct_settlement and the priced Base USDC rail (/labor/settle), so an agent can place it among ~80 siblings.

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?

Explicit preconditions: proof must be approved, the transfer must be on chain, and the payer must hold an active token offer covering the transfer (or be the packet's creator/beneficiary). It also gives the exclusions ('A stranger's junk transfer settles nothing', 'Base USDC is refused here') and points at the alternative rail, plus the 5-minute submit window.

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