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

With no annotations, the description carries the burden of behavioral disclosure. It usefully reveals that authentication, headers, and Input_0 envelope are auto-processed, and that trading APIs are gated by a server mode flag. This is valuable context, but it does not describe return formats, error behavior, rate limits, or side effects, leaving gaps for a generic API caller.

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 extremely concise: two sentences that front-load the main purpose, then provide essential procedural and conditional details. Every clause earns its place, with no wasted words or repetition.

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 generic API caller with no output schema and no annotations, the description covers the core call mechanics and the trading-mode restriction. However, it omits guidance on return value handling, error scenarios, or how to obtain a valid operationId (e.g., via list_apis). Given the tool's broad scope and complexity, this is adequate but not 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?

Schema coverage is 100%, with clear descriptions for operationId, input, and cts. The description adds critical semantics by explaining that the 'Input_0 envelope is auto-handled', saving the user from manually constructing it, and clarifies that 'input' is the payload for that envelope. This goes beyond the schema's descriptive text.

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 tool's verb and resource: it 'actually calls' the NH Open API using an operationId and input value. It is distinct from sibling tools like get_stock_price and get_stock_balance because it is a generic caller, though it does not explicitly differentiate itself or mention alternatives.

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 implies when to use the tool: to execute any NH Open API operation. It provides a clear constraint for trading APIs (only when NHPLUG_ENABLE_TRADING=true) and notes that authentication/headers/envelope are handled automatically. However, it does not explicitly say when to use it instead of the sibling convenience tools or how to discover operationIds.

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 present, but the description discloses the tool's non-executing nature by saying it returns a schema and is meant for pre-call validation. It implies a safe read operation, though it doesn't explicitly mention auth or error behaviors.

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 two-sentence Korean description is compact, front-loaded, and every word contributes to its purpose. No redundancy or 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?

Given the single parameter and no output schema, the description provides the essential return value (input schema) and the usage context. It adequately covers what an agent needs to know, including the relationship to call_api.

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 only parameter operationId is fully documented in the schema with an example. The description adds no additional parameter details beyond reaffirming that it refers to a specific operationId, so it meets the baseline for high schema coverage.

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 it returns the input field schema for a specific operationId, using the verb '반환합니다' and specifying the resource. It also distinguishes itself from the sibling tool call_api by positioning itself as a pre-check step.

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 it is used to check required parameters before calling call_api, providing a clear use case. It doesn't mention exclusions or alternatives, but the context is sufficient for an agent to know when to invoke 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?

No annotations are provided, so the description must disclose behavioral traits. It only says '조회' (inquiry), implying a read operation, but gives no details about response format, authentication, rate limits, or what exactly the balance includes. This leaves significant ambiguity for a tool with no output 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?

The description is a single, front-loaded sentence stating purpose, plus a useful parenthetical alias. No redundant words or 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?

The tool is simple with one optional parameter, but with no output schema, the description should clarify what the response contains (e.g., cash balance, holdings value). It doesn't, leaving the agent to infer the response. The core purpose is clear, but the lack of response details makes it only partially 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 schema description covers 100% of parameters (account_no), explaining the environment variable fallback. The tool description adds no additional parameter context, 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?

The description uses a specific verb '조회' (inquire) and resource '국내주식 계좌 잔고' (domestic stock account balance), clearly distinguishing it from siblings like get_stock_price (price) and list_accounts (account listing). The shortcut name adds extra clarity.

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 implies its use case by stating it inquires account balance, but does not explicitly compare with alternatives like get_stock_price or list_accounts, nor does it provide any when/when-not guidance. The usage is inferred from the purpose rather than stated.

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 burden. The verb '조회' (query) implies a read-only operation, which is a basic safety indicator. However, it does not disclose any potential side effects, rate limits, or response format beyond the name. The shortcut detail adds some implementation transparency but not deep behavioral context.

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 a single sentence with a useful parenthetical. It is front-loaded with the main purpose and adds the equivalent call_api mapping without any fluff. Every word 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?

While the tool is simple and the purpose is clear, there is no output schema, and the description does not mention what the response contains (e.g., current price only, additional market data). It is minimally viable but lacks completion on return value expectations and any usage prerequisites.

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%, with the stock_code parameter fully documented (6-digit code, example). The description adds no extra parameter meaning, but the schema already covers everything needed. Baseline 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 clearly states the tool 'queries the current price of domestic stocks' with a specific verb and resource. It also explicitly distinguishes itself from siblings by noting it is a shortcut for the call_api function krstockQuoteCurrentPrice, making its purpose unique.

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 parenthetical '단축 도구 = call_api 로 krstockQuoteCurrentPrice 를 호출하는 것과 동일' (shortcut tool = same as calling krstockQuoteCurrentPrice via call_api) provides clear context for when to use this tool instead of the generic call_api. While it doesn't explicitly list exclusions, the equivalence note gives adequate usage guidance for a simple lookup 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?

With no annotations provided, the description carries the full burden. It discloses that this is a retrieval operation ('조회'), relates to login credentials (app key/secret), has no input, and mentions the common endpoint. This implies a read-only behavior without side effects. It does not go into details like rate limits or failure modes, but for a simple list operation it is sufficiently transparent.

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 concise and front-loaded. It states the main function, purpose, and no-input condition in two clear sentences, with a parenthetical note about the endpoint. Every sentence contributes value without redundancy, making it easy for an agent to parse quickly.

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 description provides all essential context for a simple zero-parameter tool: what it does, why it is used, when to call it, and the endpoint. Although there is no output schema, the description implies the output includes account numbers (act_no) needed for subsequent operations. It could be more explicit about the response structure, but for its simplicity it is sufficiently 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 input schema is empty (0 parameters), so the baseline is 4. The description explicitly states '입력값은 없습니다' (no input value), which adds clarity beyond the schema by confirming that no parameters are accepted. This is helpful for an agent to know it should not supply any arguments.

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 tool retrieves the list of accounts connected to login credentials ('보유 계좌 목록을 조회합니다'), specifies the resource (accounts) and the action (retrieve/list). It also explains the purpose (obtaining account number before balance inquiry or order), which distinguishes it from sibling tools like get_stock_balance that likely operate on a specific account.

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 it: 'before balance inquiry/order to secure account number (act_no)'. It also notes there is no input required. However, it does not explicitly mention alternatives or conditions when not to use it, so it falls short of the highest score.

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 discloses a significant behavioral trait: order/trading APIs are only listed when the server is in trading activation mode. It also implies the tool returns operationIds. However, it does not mention authentication requirements, rate limits, or whether filters are case-sensitive/partial, leaving some gaps. Still, the disclosure of conditional visibility adds meaningful transparency beyond a trivial read operation.

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 three sentences: purpose, filtering capability, and workflow guidance plus a special condition. It is front-loaded with the main action, every sentence carries distinct information, and there is no filler. The structure efficiently communicates purpose, usage, and a key behavioral caveat 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 the tool's moderate complexity (3 optional filters, no output schema), the description covers the core purpose, workflow role, and a special display condition. It does not describe the return format (e.g., whether results are paginated or include full API metadata), but it implies the availability of operationIds, which is sufficient for the intended discovery usage. Slight incompleteness in return structure details keeps it from a 5.

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 baseline is 3. The description restates that filtering by domain/category/keyword is possible, but does not add new syntax details beyond the schema's own parameter descriptions. It reiterates the parameter names in Korean (자산군, 카테고리, 키워드) but offers no additional examples or edge-case semantics, so it adds marginal value over the 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?

The description clearly states the tool 'queries the list of endpoints' for the NH Investment & Securities Open API, with a specific verb (조회합니다) and resource (endpoint list). It differentiates itself from sibling tools by explicitly describing its role as the discovery step, distinct from describe_api/call_api and the specific data tools like get_stock_price.

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 provides explicit when-to-use guidance: 'First use this tool to find the operationId of the desired API, then proceed to describe_api / call_api.' This directly addresses workflow sequencing relative to siblings. It also explains filtering options (domain, category, keyword) and a special condition (order APIs only shown in trading activation mode), covering both usage and exclusions.

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