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

The description discloses crucial behavioral details beyond the annotations: the first call does not run the scan and only returns a $0.01 challenge; after settlement a signed authority decision is returned; receipt issuance success/failure is handled distinctly without inviting a paid retry; and payment is explicitly noted as distinct from the scanned transaction and not proof of authority. This is rich, actionable transparency that the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) do not convey.

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 description is well-structured and front-loaded: it states the core purpose immediately, then walks through the two-phase flow in chronological order. Every sentence earns its place—no filler, no repetition. It is concise yet comprehensive, covering the challenge, retry, settlement, receipt handling, and a key caveat.

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?

Given the tool's complexity (a two-step payment challenge flow), the description covers all essential aspects an agent needs: the initial challenge response, the retry with payment_signature, the signed decision, receipt outcomes, and the distinction between payment and authority. No output schema exists, but the description appropriately describes the response types and error handling. It's complete 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 86%, so most parameters already have clear descriptions (e.g., nonce, timestamp, payment_signature, transaction). The tool description adds workflow context tying payment_signature to the retry step, but it does not provide additional parameter-level meaning beyond the schema. This aligns with the baseline for high schema coverage; the description could compensate more, but it doesn't hurt.

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?

The description opens with a clear verb-resource pairing: 'scan an intended agent transaction before execution.' It names the specific purpose (fraud prevention) and distinguishes this tool from all siblings, which focus on passports, mandates, and other governance tasks. The two-step challenge workflow further clarifies what the tool actually does.

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 description explicitly states when to use the tool ('before execution') and explains the required workflow: first call returns a payment challenge, then retry with payment_signature after signing. It does not explicitly mention alternatives or when not to use, but the sibling tools are clearly different in function, and the context is unambiguous. It could be improved by referencing a sibling for other scans, but it's solid.

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