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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely new context beyond the annotations: the non-custodial guarantee ('never moves money') and the auth requirement ('Requires Authorization: Bearer <api_key>'), plus the side effect of unlocking the next milestone payment.

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?

Three short, front-loaded clauses: actor+action first, then the workflow consequence, then the non-custodial and auth facts. No filler sentences and nothing repeated from structured fields.

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 one-parameter mutation tool with no output schema and annotations covering safety, the description supplies role, effect, auth, and custody semantics. The only material gap is the unexplained trade_id, which is a notable omission for correct invocation.

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 description coverage is 0% and the single parameter `trade_id` has no description anywhere. The description implies a trade with steps and milestones but never explains what trade_id is, where to obtain it, or its format, so it fails to compensate for the coverage gap.

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+resource ('confirm delivery of the current step') and scopes the actor ('Buyer:'), which implicitly distinguishes it from the seller-side `deliver` and the read-only `get_delivery` siblings. The parenthetical '(then pay the next milestone)' adds the workflow outcome so the agent knows what the action accomplishes.

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 clear context: it is the buyer's action to confirm a step in an active trade, which follows delivery and precedes the next milestone payment. It does not name when-not to use it or explicitly route to alternatives like get_delivery or submit_payment_tx, so it stops short of full when/when-not guidance.

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