SpendPreflight

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

Annotations cover the safety profile (readOnly, idempotent, openWorld), and the description adds behavior beyond them: which external sources are queried (OFAC SDN, DNS/domain-age lookups), the possible risk outputs (low|medium|high|unknown), example flags, and a per-call price with a free trial. That is genuinely useful context an agent cannot get from the annotations alone.

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-loaded with purpose, then routing rule, then input constraint, then price. Every sentence carries distinct 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?

Because an output schema exists, the description need not enumerate return fields, and it still briefly previews the risk levels and flags. Combined with the routing rule, input constraint, and pricing, an agent has everything needed to call it correctly.

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 per-field meanings are already documented. The description nonetheless adds a cross-field constraint not expressible in the schema ('provide at least one of domain, address, or name; inputs may be combined'), which is real added meaning, though the domain format note mostly duplicates the schema example.

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 (screen a payee wallet address/name/domain) and names exactly what it checks against (OFAC SDN list, domain registration age, DNS). It is clearly distinguishable from the sibling preflight_payment, which is explicitly called out as the different tool.

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 ('standalone payee screening before paying') and when-not ('for an x402 challenge or cart and an allow/hold/block spending-rule decision, use preflight_payment instead'), naming the alternative and the condition that selects it.

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

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

Annotations already establish readOnlyHint, idempotentHint and closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: it is free, takes no arguments, and deliberately performs no payee screening or payment decision, preventing misuse as a decision tool. It stops short of describing caching/refresh behavior for pricing data, which is the only remaining gap.

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 sentences, front-loaded with the value proposition, then scope exclusions, then sibling routing. Every clause earns its place with no repetition of schema or annotation content.

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?

An output schema exists, so return values need no explanation. For a zero-argument, read-only reference tool the description supplies everything needed: what it returns conceptually, that it is safe and free, and how it relates to both siblings.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-arg tool applies. The explicit statement that it takes no arguments usefully confirms the empty schema.

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 ('read-only service reference') and enumerates exactly what it returns: prices, default spending rules, payment setup, trial allowance, integration links. It also explicitly names what it is not (no payee screening, no payment decision), which separates it cleanly from both 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?

Gives an explicit ordering cue ('Use first to learn prices...') and routes the agent to the correct alternatives by condition: check_payee for standalone payee risk, preflight_payment for an x402 challenge or cart needing an allow/hold/block decision. Nothing about when to pick this tool 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.

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=true, idempotentHint=false), and the description adds context beyond them: it never signs/settles/holds funds, each repeat call mints a new receipt and may consume another trial or paid call, and it costs $0.02 per call. The non-idempotency implication and cost are exactly the kind of behavioral detail an agent needs before retrying.

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?

Dense but front-loaded: purpose, inputs, outputs, safety, routing, and cost in that order, with no filler sentences. It is longer than strictly necessary for a tool this simple, but each sentence carries operational weight.

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?

Despite an output schema existing, the description still names the return shape (allow|hold|block, reasons, cheapest acceptable option, receipt id), and it covers nested-object inputs, cost, and the sibling alternative. Nothing needed to invoke it correctly is missing.

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 baseline is 3. The description goes further by explaining the two mutually exclusive input modes (x402 PaymentRequired challenge vs. cart) and summarizing what the rules object controls (per-payment max, hold threshold, daily cap, allowlists, new-domain days), giving semantic framing the raw schema doesn't.

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 ("Spend preflight for AI agents") plus the exact decision output (allow|hold|block). It also distinguishes itself from the sibling check_payee by naming it directly, so an agent can route without opening either 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 an explicit trigger ("Use before every payment"), names the alternative for the adjacent case ("For standalone wallet, name, or domain screening without a payment, use check_payee instead"), and clarifies that payee screening is already bundled here. When-to-use, when-not-to-use, and the alternative are all present.

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