Confirm receipt and pay the shopper

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

Annotations already declare destructive=true, readOnly=false, idempotent=false, but the description adds materially beyond them: irreversible, the two-phase preview/confirm flow, the shopper co-sign and broadcast, a warning when the shopper has not reported delivery, and the wait_seconds polling window. That is genuine behavioral detail an agent needs before committing money.

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-loads the riskiest fact ('moves money', 'Irreversible') and the preview/commit distinction before the alternative-tool routing. Every sentence carries decision-relevant information; nothing is padding.

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, and the description compensates by describing what the preview returns and what happens on confirm. Combined with annotations covering the safety profile, an agent has everything needed to invoke this correctly or route 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 100%, so the baseline would be 3, but the description adds semantics the schema does not: what confirm:true does to the flow (signs and waits up to wait_seconds on chain) and what the preview returns (payout amount, recipient, possible warning). It goes modestly beyond the structured fields.

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: sign the escrow payout to release funds to the shopper. It also positions itself in the workflow ('Step 5, moves money') and contrasts with a named sibling, open_dispute, so an agent can distinguish it without opening a 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?

Gives explicit when-to-use ('the items arrived and are right'), an explicit when-not with the alternative ('if the items did not arrive or are wrong, use open_dispute instead'), and the preview-vs-commit condition for confirm. Nothing about selection is left to inference.

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