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

Annotations only tell the agent it is a non-read-only, non-idempotent, open-world call. The description goes well beyond that: it discloses the exact price (0.4 USDC on Base), the x402 settlement mechanism, that the caller's own wallet pays, that the server never holds a wallet or pays on the caller's behalf, and that the response carries the redeemable token.

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 essential facts — PAID, exact price, and what the payment unlocks — before the redemption and wallet details. It is somewhat dense and repeats the price, but every sentence carries load-bearing information about cost, flow, or custody.

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, but the description compensates by telling the agent what the response contains (the token and how to redeem it) and naming the redemption tool. For a paid, two-step purchase flow this covers the cost, mechanics, custody, and next step an agent needs.

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 100%, so the schema already documents payment_header's shape and the two-step challenge flow, which sets a baseline of 3. The description reinforces how the parameter is used in context ('omit on your first call', 'call again with the SAME business arguments plus this field'), adding operational meaning beyond the raw field definitions.

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 ('unlocks a signed bearer token good for 100 further POST /v1/sanctions_screen calls') and explicitly differentiates from the per-call alternative by naming the price comparison. It also names the sibling needed to use the result (bundle_redeem_sanctions_screen), so the agent can distinguish it from sibling bundle tools 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 sequencing ('Call with no payment_header first to receive the payment requirements' then call again with the header) and a clear when-to-use rationale (cheaper than per-call, one settlement instead of 100). It also routes the agent to the redeem tool for the follow-up step, leaving nothing to inference.

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