BankOpenAPI

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: money arriving after cancellation will no longer be matched to the request. It does not mention irreversibility, whether a second call errors (relevant given idempotentHint=false), or what state the request ends in.

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 short sentences, front-loaded with the action and precondition. The bilingual Vietnamese/English duplication doubles the length, which is intentional for locale support but adds no new 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 one-parameter mutation tool, the description covers the eligibility precondition and the downstream consequence of cancelling. The only real gap is the return value / resulting state, which is not described despite there being no output schema.

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?

With 100% schema description coverage, the single 'id' parameter is already documented with its pr_… format and pattern. The description adds no further constraint or interpretation of the ID, so the baseline of 3 applies.

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 ('cancel') and resource ('payment request') plus a scoping precondition ('that has not received any money'). This immediately separates it from create_payment_request, get_payment_request, and list_payment_requests in the sibling set.

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 eligible condition is stated clearly: only requests that have not received money may be cancelled, which implies the when-not case (received/paid requests are out of scope). It does not name an alternative tool or explain what to do when the request already has funds, so it stops short of full routing guidance.

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?

The annotations already establish that this mutates state (readOnlyHint=false), is not idempotent (idempotentHint=false), and is not destructive. The description adds real context beyond them: the QR is a one-time dynamic bank code when the account supports it and a static VietQR otherwise, and the request auto-transitions to 'paid' once matching funds arrive. It does not mention authentication, rate limits, duplicate-request behavior, or what happens after expiry.

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 critical facts are front-loaded: the creation action, then the returned fields, then the payment reconciliation behavior. The only inefficiency is that the full content is duplicated in English after the Vietnamese, roughly doubling the length without adding 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?

Because there is no output schema, the description must explain return values, and it does so well by naming the transfer code, transfer info, qr payload semantics, and hostedUrl. What remains thin is the failure and edge-case picture: expiry behavior, what happens when a duplicate orderId is supplied, and the status before payment. These are not covered.

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 every parameter (amount bounds, orderId, description, bankAccountId default, expiresInMinutes default) is already documented in the schema. The description adds the business framing that the request is tied to an order, but no new per-parameter semantics. Baseline 3 applies.

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 names a specific verb and resource (create a payment request for an order) and then enumerates exactly what comes back: transfer code, transfer info, qr payload, and hostedUrl. Compared with its siblings, the action is unambiguous: this tool creates payment requests, not cancel/get/list requests.

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?

It implies when to use the tool by saying it is 'for an order' and that hostedUrl is 'to send to the payer'. It also notes that a payment reaches 'paid' status automatically when funds arrive with the correct code. It never states when NOT to use the tool or explicitly points to alternatives such as cancel_payment_request or get_payment_request.

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=false, so the safety profile is covered. The description adds value by naming the three fields returned (ID, email, name), which matters because there is no output schema, and by clarifying that the call is scoped to the calling key's own account.

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 sentences, front-loaded with the verb and resource, with no filler. The only cost is the bilingual duplication, which repeats the same content rather than adding structure or detail.

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 zero-parameter read tool with annotations covering the safety profile, the description supplies what is missing from structured data: which account is fetched and which fields come back. It does not mention failure modes (e.g., invalid or expired key), but nothing essential for correct invocation is absent.

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 the baseline is 4. The description usefully confirms that identity comes from the API key rather than from any input, which is exactly the semantic point an agent needs.

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 ('Get the BankOpenAPI account that owns this API key') and previews the returned fields (ID, email, name). It is clearly separable from the payment/balance/transaction siblings, though it does not explicitly contrast itself with any of them.

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: the phrasing 'that owns this API key' tells the agent the account is resolved implicitly from credentials, so no lookup arguments are needed. There is no explicit when-to-use versus when-not guidance, but with no sibling covering account metadata the risk of mis-selection is low.

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=false, so safety is covered. The description goes beyond that by disclosing a genuine business rule: once the free turns are exhausted and the balance is at or below zero, notifications are suspended. It stops short of saying whether this call itself consumes quota or whether the reading is instantaneous, which would have justified a 5.

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 balance figure is front-loaded and each sentence carries the business rule without filler. The one cost is that the content is duplicated verbatim across Vietnamese and English, roughly doubling the text without adding information, though that is a defensible bilingual design choice rather than 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?

For a zero-parameter read with no output schema, the description names both returned values (balance in VND, remaining free notifications) and the condition that suspends notifications, which is enough to call it and interpret the result. Missing only edge details such as whether the free quota resets on a calendar month boundary or on account anniversary.

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, which is the baseline-4 case, and the description correctly does not invent any. No confusion is possible about inputs since additionalProperties is false and the object is empty.

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 concrete read: prepaid balance in VND plus the count of free notification transactions remaining this month. That is a specific verb-plus-resource pair an agent can match to a user request. It is only slightly weakened by not distinguishing itself from the neighbouring get_account, which an agent could plausibly confuse with a balance lookup.

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?

No explicit when-to-use or when-not-to-use guidance is given, and no sibling tool is named as an alternative. Usage is only implied by the described business rule about notifications pausing, which hints at 'check this before sending a notification request' without ever saying so. Adequate but leaves routing 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 already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral value by naming the returned data (status, amount received, matched transactions) since no output schema exists, but it omits error/not-found behavior and any pagination or expansion options.

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 short clauses, front-loaded with the action and followed by the returned fields; nothing is padded. Length is doubled by the Vietnamese/English duplication, but that appears to be a house convention rather than filler.

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-ID read tool with one fully documented parameter, the definition covers what an agent needs: what it fetches and what comes back. The absence of an output schema is partly offset by enumerating the returned fields, leaving only not-found behavior unspecified.

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?

Only one parameter and schema coverage is 100%, with the schema itself documenting the pr_… pattern. The description adds nothing about the ID beyond what the schema already states, so the baseline 3 applies.

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+resource ("Xem một yêu cầu thanh toán" / "Get a payment request") and enumerates what the response covers (status, received amount, matched transactions). The singular article "một" implicitly distinguishes it from list_payment_requests, though no sibling is named 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: fetch one request by ID rather than listing. There is no explicit when-to-use versus list_payment_requests, no prerequisites, and no note on what to do when the record is missing or cancelled (cancel_payment_request is a sibling).

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=false, so the safety profile is covered. The description usefully adds the "newest first" ordering, which is behavioral information absent from the schema, but says nothing about pagination, whether more than `limit` results can be retrieved, or what a returned payment request contains.

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 short clauses with the resource and sort order front-loaded, followed by filtering capability. The bilingual Vietnamese/English duplication doubles the character count but is a consistent localization convention rather than filler prose.

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?

This is a simple three-parameter read tool with full schema coverage, no required params, and annotations that cover the safety and scope profile. The only meaningful omission is pagination behavior, which the absence of an output schema makes slightly more consequential but not disqualifying.

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 enum meanings (open/paid/attention/closed) are fully spelled out in the schema, including the under/overpaid nuance. The description only restates that filtering is by status group or order ID, adding no format, matching, or combination semantics beyond what the schema already provides.

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 names a specific verb and resource ("Liệt kê yêu cầu thanh toán") and adds the default sort order ("mới nhất trước"), so an agent immediately knows this is a collection read of payment requests. It does not explicitly contrast with get_payment_request or list_transactions, but the list-vs-single distinction is self-evident from the naming.

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?

"Lọc theo nhóm trạng thái hoặc mã đơn hàng" implies the filtering use case and the word "optionally" signals all filters are optional. However, there is no explicit statement of when to prefer this over get_payment_request (single lookup by ID) or list_transactions, and no guidance on paging through results when the limit is hit.

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?

The annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context — the result order (newest first) and that only linked bank accounts are covered — but says nothing about truncation, pagination, or what happens when the limit is hit, which matters for a list tool with a hard 100-item cap.

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 short sentences, well front-loaded with the resource and scope before the ordering detail. The Vietnamese/English duplication mirrors the bilingual schema and serves the likely audience, though it does double the length for a single fact.

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 all-optional parameters, full schema coverage, annotations, and no output schema, the description covers enough to call the tool correctly. It is incomplete about result-set behavior — no mention of whether more than 'limit' rows exist or how to page — which is the main gap for a filtering list tool.

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 all four parameters (from, to, type, limit) are already documented with format, enum meaning, defaults and Vietnam-time semantics. The description's 'newest first' and 'money in/out' phrasing loosely maps to the type filter but adds nothing the schema does not already state, so the baseline 3 applies.

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 names a specific verb and resource ('List bank transactions') plus the scope ('on linked accounts') and the money-in/out qualifier, so an agent can tell it apart from get_balance or list_payment_requests. It stops short of explicitly contrasting itself with the payment-request siblings, which is the only thing keeping it from a 5.

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: 'on linked accounts, newest first' suggests browsing transaction history, but there is no statement of when to prefer this over list_payment_requests or get_balance, and no exclusions or prerequisites. An agent must infer the choice from the tool name alone.

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