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

Beyond the annotations, the description discloses that the QR code is dynamic, that the result is returned both as a URL (deeplink + hosted image) and as an inline PNG, and that the caller must poll with wait_for_payment. This adds useful behavioral context beyond the simple readOnly/idempotent/destructive flags and does not contradict the annotations.

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 English description is concise and front-loaded: purpose, return format, and follow-up action in three sentences. The Japanese translation is redundant for an AI agent and doubles the length, but it is placed after the English and does not obscure the key information.

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 tool with no output schema, the description does a good job of stating what is returned (URL and inline PNG) and what the caller should do next (poll with wait_for_payment). Combined with the fully documented input schema, this covers the essential workflow, though it omits details like error conditions or QR expiration.

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%, and the schema already explains amount, order_description, redirect_url, merchant_payment_id, and other fields in detail. The tool description adds no parameter-level meaning, so the baseline of 3 is appropriate; the schema carries the parameter documentation burden.

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 specific verb and resource: 'Create a dynamic PayPay QR code that a customer can scan to pay.' It clearly identifies the tool's function and distinguishes it from the sibling tools (get_payment_details, delete_qr_code, wait_for_payment) by framing it as the creation step, not a lookup, deletion, or polling operation.

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 gives explicit follow-up guidance: 'Use wait_for_payment to poll until the customer completes the payment.' This tells the agent what to do after calling this tool. It does not explicitly contrast with get_payment_details or delete_qr_code, but the creation-oriented wording makes the appropriate context clear.

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 carry destructiveHint=true, readOnlyHint=false, and idempotentHint=true. The description adds valuable behavioral context by stating the invalidation happens only before payment and cannot be used afterward. This goes beyond the structured annotations without contradicting them.

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 front-loaded with the core behavior and includes a clear use-case sentence. The Japanese translation doubles the length, but it is intentional localization rather than filler, so the structure remains efficient.

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 single-parameter tool with rich annotations and no output schema, the description covers the essential operational context: purpose, timing constraint, and when to use it. It does not describe error behavior or return values, but those are less critical for this simple invalidation operation.

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%, and the code_id property is already documented as "The codeId returned from create_qr_code (NOT the merchantPaymentId)." The tool description itself adds no additional parameter-level meaning, so the baseline of 3 is appropriate.

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 states a specific verb and resource: "Invalidate a QR code before it is paid." It clearly defines the tool's scope and distinguishes it from siblings by emphasizing the pre-payment invalidation purpose, which separates it from create_qr_code, get_payment_details, and wait_for_payment.

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 gives explicit when-to-use guidance: "Use this when an order is canceled before checkout, or to clean up expired codes." It also states a clear exclusion: "Cannot be used after payment has completed," so an agent knows the boundary without ambiguity.

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 declare readOnlyHint=true and openWorldHint=true, so the description doesn't need to repeat safety. It adds value by disclosing the return statuses and the polling-vs-one-off distinction, which is useful behavioral context. It doesn't contradict annotations and provides extra detail beyond them.

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?

Two compact paragraphs (English and Japanese) that front-load the purpose and statuses, then give usage guidance. No redundant sentences; every line 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?

With only one parameter, no output schema, and read-only annotations, the description covers the essential: what it does, the parameter source, and when to use it. It could mention the response structure beyond statuses, but for a simple status check it is sufficient.

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 description for merchant_payment_id is already present (100% coverage), and the description adds context by noting it's 'the merchantPaymentId used when creating the QR code', helping the agent locate the correct identifier. This goes beyond the schema's basic type definition.

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 clearly states the action (fetch status and details) and the resource (payment by merchantPaymentId). It lists the exact possible statuses, distinguishing it from sibling tools like wait_for_payment. The purpose is unambiguous and specific.

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: 'Use this for one-off status checks. For active polling, prefer wait_for_payment.' This gives clear context and directs to an alternative, leaving no ambiguity about when to select this tool.

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 provide readOnlyHint=true, which already signals no state mutation. The description adds valuable behavioral context beyond that: it explicitly mentions the polling action, the timeout behavior, and that it returns final status and full payment detail. It also discloses the default 2–3s polling interval, which is not in the annotations. No contradictions found, and the description augments the safety profile with concrete operational details.

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 English portion is concise and front-loaded: the first sentence states the core purpose (poll until terminal or timeout), and subsequent sentences add default interval and return value. The Japanese duplicate doubles length but is likely intentional for localization. The structure is well-organized with no wasted words, though the duplication could be trimmed for a purely English audience.

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?

The tool has 3 parameters, all fully described in the schema, and no output schema. The description covers the core behavior (polling, terminal states, timeout, return of final status and details) and integrates well with the annotations. A minor gap is the lack of explicit behavior on timeout (e.g., does it return the last status or raise an error?), but overall it provides enough information for an agent to correctly invoke the tool. Sibling tools are distinct, and this description sufficiently differentiates it.

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%, and each parameter (merchant_payment_id, timeout_seconds, poll_interval_seconds) has a clear description and defaults/min/max. The description itself adds little beyond the schema—it mentions the default polling interval, but that's already in the schema ('default 3', 'PayPay recommends 2–3s'). It does not introduce new meaning for the parameters, so a baseline of 3 is appropriate.

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 states a specific verb (poll), resource (PayPay payment), and the exact terminal states it waits for (COMPLETED, AUTHORIZED, REFUNDED, FAILED, CANCELED). It clearly distinguishes itself from siblings like get_payment_details (which likely returns a one-time snapshot) and create_qr_code/delete_qr_code (which create/delete resources). The purpose is unambiguous and directly tied to its name.

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 implicitly tells when to use this tool: when you need to wait for a payment to reach a terminal state, as opposed to fetching a single status snapshot. While it doesn't explicitly name the alternative (get_payment_details) or state 'use this instead of X', the context is clear from the polling behavior. It lacks explicit exclusions or 'when not to use' guidance, but the intended use case is well communicated.

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