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

With no annotations, the description carries the full burden and does well: it discloses the end-to-end side effects (on-chain payment, credential saving), the idempotency constraint (each quote creates a new invoice), and the precise recovery path via fulfill_payment. It omits auth requirements, rate limits, and return format, leaving some behavioral gaps.

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?

Highly front-loaded ('PREFERRED.' plus the workflow) and every sentence carries distinct operational weight — constraints, sequencing, and recovery are all packed without redundancy.

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 no annotations and no output schema, the description covers the critical operational context well: purchase flow, idempotency, and error recovery. It falls short on documenting the four input parameters, which an agent still needs to invoke 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 description coverage is 0% for 4 parameters, so the description must compensate but largely does not. It only alludes to dry_run's semantics via the 'do not call dry_run then buy again' warning and says nothing about plan, country, or network formats.

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 ('Buy VPN in one call') and enumerates the full internal pipeline (quote → pay on-chain → fulfill → save credentials). It clearly distinguishes itself from siblings by referencing fulfill_payment and the dry_run path, so an agent can route without opening any 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/when-not guidance: call ONCE per purchase, do not use curl/shell against /pay, do not dry_run then buy again, and if it errors after payment use fulfill_payment instead. It names the alternative tool and the exact condition selecting 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?

With no annotations, the description carries the burden and does well: it declares the tool does not create an invoice or send money (non-destructive, idempotent-looking recovery), and requires artifacts from a prior call. It doesn't state auth requirements or what happens if the inputs are stale/invalid, so a small gap remains.

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 sentences, tightly front-loaded with the 'Recovery only' scope before the requirements and the negative guidance. Every sentence earns its place.

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?

No annotations and no output schema, so the description must stand alone; it covers purpose, prerequisites, and exclusions well. It stops short of describing what the returned VPN credentials look like or how errors/failed recovery are surfaced, and it ignores the optional country field.

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%, so the description must compensate, and it does partially: it names the four required parameters and tells the agent where they come from (prior buy_vpn/sign_and_pay). It adds no format or validation detail for invoice_no, payment_signature, settlement_tx, and never mentions the optional 'country' parameter.

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 (exchange) and resource (already-broadcast payment → VPN credentials) plus an explicit scope qualifier ('Recovery only'). It also distinguishes itself from siblings by naming buy_vpn/sign_and_pay as the source of the required inputs.

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?

Explicitly states when to use it ('when fulfill failed after payment') and when not to ('never call buy_vpn again', 'does not create a new invoice or send money'). The alternative is named and the triggering condition is given, 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.

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

No annotations are provided, so the description carries the full burden. It usefully discloses the data source ('X402_BASE_URL discovery') and that the result is a list of purchasable items, implying a safe read, but it says nothing about auth requirements, rate limits, caching, or failure modes.

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?

One dense sentence, front-loaded with the verb and the primary resource, with the returned fields tucked into a compact parenthetical. Nothing is wasted.

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?

With no output schema and no parameters, the description compensates well by enumerating the return contents (id, USD price, duration, country codes). It is close to complete for a simple discovery call, though auth/access expectations for the X402_BASE_URL endpoint remain unstated.

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 schema declares zero parameters, so there is no parameter semantics to convey and the baseline of 4 applies. The description correctly signals a no-argument call.

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 gives a specific verb ('List') plus a precisely scoped resource ('purchasable VPN plans ... and supported server country codes'), and even names the fields returned. This is clearly distinguishable from the write/payment siblings (buy_vpn, sign_and_pay) without opening any 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?

Usage is only implied: an agent can infer this is the pre-purchase discovery call, especially given the buy_vpn sibling, but the description never says when to call it or that it precedes a purchase. No alternatives or exclusions are named.

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?

No annotations are provided, so the description carries the full burden and does so well: it discloses the irreversible side effect (real on-chain broadcast), the missing outcome (no VPN credentials fetched), the required follow-up call, and the double-charge failure mode. These are precisely the behavioral traits an agent cannot infer from the schema.

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 tight sentences, warning first, recommendation second, mandatory follow-up third. No filler, and the highest-risk information (DEBUG ONLY, double charge) is front-loaded.

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?

With no output schema, the description usefully names the returns (payment_signature, settlement_tx) and the required continuation, which is the critical path context for a payment tool. The remaining gap is parameter-level detail for a 0%-coverage schema, notably dry_run.

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 description only indirectly touches one parameter, the invoice_no that must be reused in fulfill_payment. The nested 'accepts' array structure, dry_run, and network are not explained anywhere, so the description only partially compensates 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 and resource ('Broadcasts on-chain payment') plus concrete return values, and immediately marks it as DEBUG ONLY, which distinguishes it from the sibling buy_vpn. An agent can tell what it does and what it is not for without opening the 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?

Explicit routing: 'Prefer buy_vpn', plus a mandatory next step ('you MUST next call fulfill_payment with the same invoice_no') and two named prohibitions (never curl /pay, never call buy_vpn again due to double charge). This is exactly the when/when-not/alternatives guidance the dimension asks for.

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?

With no annotations, the description carries the full burden. It does disclose one meaningful behavioral trait (addresses only, never private keys), which signals a safe read, but says nothing about permissions, what happens when no wallets are configured, or any limits.

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?

A single sentence with no filler, front-loading the verb and resource and appending the one detail worth knowing (no private keys). Every clause earns its place.

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 simple zero-param read tool with no output schema, the description states what is returned at a high level (configured wallet addresses) and removes the obvious security ambiguity. It could say a bit more about the return shape or the empty-configuration case, but it is essentially complete.

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 beyond what the empty schema already shows. Baseline 4 for a parameterless tool.

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 gives a concrete verb+resource ("Show which wallets are configured") and adds a scope qualifier about what is and isn't returned. It is clearly distinguishable from the payment/VPN siblings, though it does not name them explicitly.

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?

Usage is only implied: an agent would call this to inspect configured wallets. There is no statement of when to use it versus alternatives, nor any prerequisites or exclusions, so it sits at minimum viable.

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