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

With no annotations, the description must carry the behavioral disclosure burden. It does disclose key actions: server downloads the document, parses it, generates Excel, validates it, and returns only the path; it also does not return the original disclosure text. It explains that allow_body defaults to false and refuses to generate the body unless explicitly approved. However, it omits potential failure modes, such as what happens if validation fails, and doesn't mention side effects like file overwriting or server resource usage. These are notable gaps given the lack of annotation support.

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 structured logically: a concise purpose statement, a brief behavior note, then a clear Args list. Every sentence adds value; there is no filler. The critical constraint about candidate_id and the allow_body condition are front-loaded, and the parameter list is easy to scan. It is neither overly verbose nor under-specified.

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, no output schema, and no annotations, the description covers the essential aspects: what it does, input requirements, output behavior (path only), and the approval gate for allow_body. Minor omissions include lack of explicit error handling/return format details on failure and clarification that the output directory must already exist. These are not critical for invoking the tool correctly, so a 4 is appropriate.

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 fully compensate. Every parameter is explained in the Args section: candidate_id must come from list_financial_document_candidates (and should not be manually constructed), scope has explicit enum values (consolidated/separate), output_dir must be an existing writable directory, output_name includes a filename example with .xlsx, and allow_body has a condition and default behavior. This goes well beyond the bare schema titles and adds critical operational meaning.

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 ('makes'), a specific resource ('validated financial statements Excel'), and a clear outcome ('returns only the path'). It also explains the server-side behavior (download, parse, create, validate) which distinguishes it from the many retrieval get_* siblings. No ambiguity about what this tool does.

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 provides clear context on how to use it: it references list_financial_document_candidates for candidate_id and specifies that candidate_id must be taken from there. It also gives an explicit condition for allow_body (only after user approval when audit/review reports are absent). While it doesn't explicitly say 'use this instead of sibling get_* tools,' the tool's unique create nature and the reference to the candidate list make the usage 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?

No annotations are provided, so the description carries the full burden. It describes a read-only retrieval with no side effects, which is acceptable for this type of tool. However, it does not disclose any potential constraints like data availability, authorization, or rate limits, leaving some behavioral traits implicit.

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 very concise: a single line stating the purpose followed by a parameter list. Every sentence adds value, no redundancy, and it is front-loaded with the core intent.

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 simplicity (3 required params, no output schema, read-only), the description is adequate but could be enhanced. It explains the parameters but does not describe the return format or data structure, which might be important for an agent to properly use the output. For a retrieval tool, specifying the response fields would improve completeness.

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 has 0% coverage (no parameter descriptions in the JSON schema), but the description's 'Args' section fully explains each parameter: corp_code as 8-digit DART code, bsns_year as YYYY, and reprt_code with specific report codes. This adds essential meaning beyond the schema's titles.

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 audit fee status (감사보수 현황) in Korean, matching its name. The verb '조회' (inquiry) and resource are specific, and the tool is distinct from siblings like get_audit_opinion or get_non_audit_service.

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 does not explicitly state when to use this tool versus alternatives. However, the name and context imply it is for audit fee records, and the parameter list is provided. No exclusions or alternative suggestions are given, so usage guidance is implied but not explicit.

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 provided; description does not disclose read-only nature, authentication requirements, rate limits, or error behavior. For a data retrieval tool, stating it is a read operation would be expected.

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?

Extremely concise: one sentence for purpose, then a well-structured parameter list. No wasted words, front-loaded with key info.

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?

Lacks output schema and does not describe return format or error handling. For a simple retrieval tool, this is minimally adequate but could be improved by noting the output structure (e.g., 'returns auditor name and opinion text').

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 has 0% description coverage, but the description explains each parameter with format (8-digit code), year format, and report codes with examples. This fully compensates for schema gaps.

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?

Description clearly states 'retrieve name of auditor and audit opinion', which is the core purpose. However, it does not explicitly distinguish from siblings like get_audit_fee, but the name itself aids differentiation.

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 guidance on when to use this tool versus other audit-related tools (e.g., get_audit_fee) or general disclosure search. The description only explains parameters, not usage context.

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, and the description does not disclose behavioral traits such as idempotency, side effects, authentication requirements, or response characteristics. The description is minimal and fails to inform about the tool's safety or operational impact.

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: one sentence explaining the purpose, followed by a clear list of parameters with format hints. Every word adds value, and the structure 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 and minimal description, the tool lacks critical context such as return value structure, pagination, error handling, or rate limits. For a data retrieval tool with 3 parameters, it is minimally adequate but leaves gaps in completeness.

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 description adds meaning beyond the schema by specifying the format for corp_code (8-digit DART code) and the date format (YYYYMMDD) for bgn_de and end_de, along with optionality. This compensates for the 0% 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 explicitly states the tool retrieves key bankruptcy occurrence information from a major report. The name 'get_bankruptcy_report' aligns with the description, and it is distinct from sibling tools like 'get_rehabilitation_report'.

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 lists parameters but does not provide explicit guidance on when to use this tool versus alternatives (e.g., rehabilitation report). It implies usage for bankruptcy data but lacks 'when to use' or 'when not to use' context.

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, and the description does not disclose behavioral traits such as read-only nature, authentication needs, rate limits, or data freshness. For a tool without annotations, the description should carry this burden but only mentions parameter usage.

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?

Description is short and front-loaded: a purpose sentence followed by clear parameter explanations. No unnecessary 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 simple retrieval tool with three parameters and no output schema, the description provides sufficient information for an agent to understand the function and required inputs. It lacks details on return format or pagination, but is adequate given the context.

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%, but the description fully compensates by explaining all three parameters: corp_code (8-digit unique number), bsns_year (YYYY format with example), reprt_code (four report types with codes). This adds critical meaning beyond the schema titles.

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?

Description clearly states it retrieves corporate bond issuance and redemption performance (회사채 발행 및 상환 실적). This specific verb+resource combination distinguishes it from siblings like get_convertible_bond, get_exchangeable_bond, get_corp_bond_outstanding, etc.

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 guidance on when to use this tool versus alternatives. The description only provides parameter details but no context about when to prefer this over sibling tools like get_debt_securities or get_corp_bond_outstanding.

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 behaviors. It does not mention whether the operation is read-only, destructive, requires authentication, or has rate limits. The description is purely functional, offering no additional 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 reasonably concise with two parts: a brief sentence and an Args section. The Args section repeats parameter details but is organized. Could be slightly tighter, but overall 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?

Given no output schema, the description does not explain return values or pagination. It covers purpose and parameters but lacks usage guidelines and behavioral traits. For a basic retrieval tool among many siblings, it is adequate but has gaps.

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 description explains each parameter beyond the schema: corp_code is a DART corporate unique number (8 digits), bgn_de and end_de are dates in YYYYMMDD format and optional. This adds meaningful context, especially since schema coverage is 0%.

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 retrieves '신주인수권부사채권 발행결정' main information from major reports. The verb '조회' indicates a query operation. However, it does not differentiate from sibling tools like get_bond_issuance, get_convertible_bond, etc., which are similar.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, limitations, or exclusions. The description only explains what the tool does, not its appropriate context.

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 provided, so description must carry burden. It indicates a read operation ('조회') but lacks details on permissions, rate limits, error handling, or what happens when no results. Minimal but not misleading.

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?

Description is concise with a clear purpose sentence followed by parameter list. The Args block slightly rephrases schema but is acceptable. No redundant 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?

With no output schema and no annotations, the description fails to provide context on return format, pagination, or connection to other tools. Given the many sibling tools, more context on when to use this specific one is needed.

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%, but the description adds meaning for all three parameters: corp_code is a DART 8-digit code, dates are in YYYYMMDD format with optional status. This compensates for schema gaps, though format details are brief.

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?

Description clearly states it retrieves business acquisition decision information from major matters reports. The verb '조회합니다' (retrieves) is specific and the subject '영업양수 결정' distinguishes it from siblings like get_business_transfer or get_equity_investment_acquisition, though not explicitly differentiating.

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 guidance on when to use this tool versus siblings or under what conditions. The description does not mention prerequisites, recommended scenarios, or exclusions.

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 carry the full burden. It only states the purpose ('inquiry') but omits any behavioral traits such as read-only nature, authentication needs, rate limits, or what happens if no data is found. The minimal description does not compensate for missing 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 description is concise: one sentence for purpose and a short parameter list. It front-loads the purpose. However, the parameter details could be integrated into a single sentence rather than a separate block, but it 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 simple query tool with 3 parameters (1 required) and no output schema, the description covers purpose and parameter meanings. However, it lacks information about return values, pagination, error handling, or how to differentiate from sibling tools, making it minimally adequate.

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 has 0% description coverage for parameters, but the description includes an 'Args' section that adds meaning: corp_code is an 8-digit DART company code, bgn_de and end_de are optional dates in YYYYMMDD format. This significantly helps an agent understand parameter semantics beyond the bare schema titles.

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 business suspension information from a specific report (영업정지 - 주요사항보고서). The verb '조회' (inquiry) and resource are explicit. However, among many sibling report tools (e.g., get_bankruptcy_report, get_rehabilitation_report), it does not differentiate itself, so it loses a point.

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 guidance on when to use this tool versus alternatives. Given the large number of sibling report tools, the description should indicate scenarios or prerequisites for business suspension queries. It provides none.

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 full responsibility for behavioral disclosure. It does not mention read-only nature, authentication requirements, rate limits, or any side effects. The term '조회' hints at a retrieval operation, but this is implicit and insufficient for safe invocation.

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, consisting of a single purpose sentence followed by a parameter list. No unnecessary words or redundancy. The front-loaded sentence immediately conveys the tool's primary function.

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 covers the tool's purpose and parameter formats but lacks details about the return value (no output schema) and does not indicate which parameters are required (though inferred from schema). For a simple retrieval tool with three parameters, the coverage is adequate but not exhaustive.

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 description adds meaningful format details beyond the input schema: corp_code is specified as an 8-digit DART company code, and bgn_de/end_de are date strings in YYYYMMDD format. Since schema description coverage is 0%, this compensation elevates the score above baseline.

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 (조회하다 - inquire/retrieve) and resource (영업양도 결정 - business transfer decision from major matters report), which clearly identifies the tool's function. It distinguishes from siblings because siblings cover different corporate actions such as audit fees, bankruptcy, bond issuance, etc.

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 guidance is provided on when to use this tool versus its alternatives (e.g., other get_* tools for different corporate events). There is no mention of prerequisites, context, or exclusions, leaving the agent to infer usage solely from the name and description.

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 provided, and the description fails to disclose behavioral traits such as read-only nature, authentication requirements, error handling, or limits. The description only states what it does, not its side effects.

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?

Single paragraph plus parameter list is concise. Main purpose is front-loaded. Could be slightly more structured with separate sections.

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?

Adequate for a simple retrieval tool with required parameters, but missing output description. No output schema exists, so the agent has no idea about the return structure. Could mention what data fields are returned.

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%, but the description provides detailed semantics for each parameter: corp_code (8-digit DART code), bsns_year (YYYY format), reprt_code (with example codes). This adds significant meaning beyond schema titles.

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 explicitly states it queries capital increase/reduction history. The verb '조회합니다' (query) and resource '증자(감자) 현황' are clear. However, it doesn't distinguish from sibling tools like get_capital_reduction (which might be more 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?

No guidance on when to use this tool vs alternatives like get_capital_reduction or get_free_capital_increase. No prerequisites or exclusions mentioned.

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 full burden for behavioral disclosure. It only implies a read operation via '조회합니다' but does not mention authentication needs, rate limits, return format, or any side effects. Significant gaps exist.

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 with a single main sentence followed by an Args section. Every part serves a purpose, and the key information is front-loaded. No 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?

The description explains the source (주요사항보고서) but does not describe the return values or output structure. Given no output schema, this is a notable omission. The parameter list is well covered, but overall completeness is adequate but not comprehensive.

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 description adds meaning beyond the schema by explaining each parameter: 'corp_code' as 8-digit DART code, 'bgn_de' and 'end_de' as date range with format. Since schema description coverage is 0%, this provides valuable guidance.

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 verb ('조회합니다' - queries) and the resource ('감자 결정 정보' - capital reduction decision information), providing a specific purpose. While the sibling list contains many capital-related tools, the name and description together distinguish it well.

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?

There is no guidance on when to use this tool versus alternatives or any conditions/usage notes. The description only states what the tool does, not when it is appropriate.

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?

Without annotations, the description must communicate behavioral traits. It indicates a safe read operation but does not disclose any further details like authentication requirements, rate limits, or what happens if no data is found. The parameter format hints add some transparency, but overall the description is minimal for a tool with zero annotation coverage.

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 well-structured. It starts with a clear one-line purpose, then uses a bullet-like list for parameters with format explanations. Every sentence adds value with no 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?

For a simple read operation with three well-explained parameters, the description is largely complete. It lacks output schema details and error handling information, but given the low complexity and the presence of similar sibling tools providing context, it is sufficiently informative for an agent to use the tool 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?

The schema has 0% description coverage, leaving the description to fully explain parameters. The description provides explicit formats: corp_code as 8-digit DART code, bsns_year as YYYY, reprt_code with enumerated report types and examples. This adds substantial meaning beyond the schema titles, making the parameters self-documenting.

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 outstanding balance of commercial paper securities (기업어음증권 미상환 잔액). The verb '조회합니다' indicates a read operation. This distinct resource (commercial paper) differentiates it from sibling tools like get_corp_bond_outstanding or get_debt_securities_outstanding.

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 guidance is provided on when to use this tool instead of related siblings. There is no mention of prerequisites, alternatives, or exclusions. The parameter descriptions offer format constraints but do not help an agent decide between this and other debt-related tools.

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 implies a read operation but does not explicitly state it is read-only, safe, or idempotent. It also does not disclose potential side effects, permissions, or error handling. The parameter constraint (8-digit DART code) is mentioned, but broader behavioral traits are missing.

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: one sentence explaining the purpose followed by a brief parameter note. It is front-loaded with the main function, contains no redundancy, and every word adds value. The structure is clean and easy to parse.

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 simplicity (one parameter, no output schema), the description is fairly complete. It lists example return fields, which compensates for the lack of an output schema. However, it could be more precise about the exact payload structure or potential variations, which would improve completeness.

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 provides no description for 'corp_code' (0% coverage). The description compensates by specifying that corp_code is the DART company unique number, 8 digits, and required. This adds crucial context beyond the schema's type-only definition, helping the agent understand the parameter's format and origin.

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 basic company information, listing specific fields (company name, representative, business number, address, etc.). The verb '조회' (retrieve) and resource '기업의 기본 정보' (basic company info) are specific. Among many sibling tools that focus on specific financial or corporate data, this tool's purpose is distinct and well-defined.

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?

There is no guidance on when to use this tool versus its many siblings. The description does not mention prerequisites, alternatives, or scenarios where another tool might be more appropriate. The long list of sibling tools highlights the need for such guidance, but it is absent.

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 carry the full burden. It only implies a read operation ('조회합니다') but does not explicitly state it is read-only, nor does it mention any side effects, authentication needs, rate limits, pagination, or response format. The transparency is minimal.

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, consisting of a single sentence followed by a parameter list. It is front-loaded with the main purpose. However, mixing Korean and English without clear separation may slightly hinder clarity for a non-Korean agent, but overall it is 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?

Given the complexity of the tool (3 parameters, no output schema, many siblings), the description is insufficient. It does not explain what the returned data looks like, which is critical since there is no output schema. The agent cannot infer the structure of the response.

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 description adds meaning to each parameter: corp_code is 'DART 기업 고유번호 (8자리)', bgn_de is '시작일 (YYYYMMDD)', end_de is '종료일 (YYYYMMDD)'. However, it does not clarify which parameters are required (only corp_code is required per schema) and does not mention optionality. Schema coverage is 0%, so the description partially compensates but misses some critical details.

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 '상각형 조건부자본증권' (conditional capital issuance) decision information from a report. The verb '조회합니다' indicates a retrieval operation. It is specific among many similar sibling tools that deal with different financial instruments.

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 provides no guidance on when to use this tool versus alternatives. Among many sibling tools for various financial reports, the agent is not told when to choose this one over others like get_convertible_bond or get_hybrid_bond.

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 are absent, so the description must carry the burden of behavioral disclosure. It states the function is a retrieval operation (read-only implied) but does not mention authorization needs, potential rate limits, or what happens if the corporation code is invalid or data is missing. No behavioral traits beyond the basic operation are disclosed.

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: one sentence stating the purpose, followed by a clean Args section listing parameters. No extraneous information. Every sentence serves a purpose, and the key action 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?

The description provides the data source (주요사항보고서) and parameter details, which is adequate for a simple retrieval tool. However, without an output schema, the description should hint at the structure of returned data; it only says '주요 정보를 조회합니다' (retrieves main information), which is vague. No error handling or edge cases are mentioned.

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 description includes an 'Args' section that explains each parameter: corp_code as an 8-digit DART company code, bgn_de and end_de as optional dates with format YYYYMMDD. This adds meaning beyond the input schema, which only lists types and titles. However, it does not elaborate on default behavior or range constraints.

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?

Description clearly states the tool retrieves 'convertible bond issuance decision' information from a specific report (주요사항보고서). The verb '조회합니다' (retrieves) and resource '전환사채권 발행결정' are specific. Among siblings like get_bond_issuance or get_exchangeable_bond, the name and purpose differentiate it, though no explicit differentiation is mentioned.

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 guidance is provided on when to use this tool versus alternatives, such as get_bond_issuance or get_exchangeable_bond. There are no prerequisites, exclusions, or context hints for usage.

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 implies a read-only operation by stating 'retrieves', but does not explicitly disclose side effects, authentication needs, or rate limits. The description is adequate but not comprehensive.

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, front-loading the main purpose, followed by clearly listed parameter explanations. Every sentence adds value with no 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?

While the parameter descriptions are helpful, the description lacks details about the response structure (no output schema) and prerequisites (e.g., needing corp_code from get_corp_codes). Given the tool's simplicity and lack of annotations, these omissions reduce completeness.

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 has zero description coverage, but the description's Args section provides meaningful explanations for all three parameters, including the DART corporate code format, business year example, and report code mapping. This compensates well for the schema gaps.

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 outstanding balance of corporate bonds using a specific verb (조회합니다) and resource (회사채 미상환 잔액). The name itself differentiates from siblings like get_bond_issuance or get_convertible_bond.

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 guidance is provided on when to use this tool versus its siblings, such as get_bond_issuance or get_debt_securities_outstanding. The description only lists parameters without contextual usage advice.

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 behavioral traits: the tool downloads the entire list (110k+ entries) and filters locally, and it does not return the full list if no parameters are given. This transparency helps the agent understand performance and data handling.

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 well-structured: an introductory sentence, a paragraph explaining the limitation, and a bullet-like argument list. It is clear and informative, though a bit verbose; still, every sentence adds value.

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 output schema, the description does not specify the return format (e.g., list of objects with corp_code and name). While the purpose is clear, the agent might benefit from knowing what fields are returned. For a lookup tool with many sibling tools, completeness is adequate but not perfect.

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 0%, so the description must fully explain parameters. It does so: corp_name is a partial match (case-insensitive, Korean/English), stock_code is an exact 6-digit code. This adds essential meaning beyond the schema's minimal type and default.

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 explicitly states the tool searches for DART unique codes (corp_code) by company name or stock code. The verb 'search' and resource 'DART 고유번호(corp_code)' are specific and clear, effectively distinguishing it from sibling tools which retrieve specific financial reports.

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 provides clear usage context: it explains that the DART API does not support direct company name search, so the tool downloads the entire list and filters server-side. It also states that at least one parameter must be specified and warns that omitting both will not return the full list. This gives good guidance on when to use the tool, though it does not explicitly compare to siblings.

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 fully disclose behavior. It indicates a read operation but does not mention side effects, permissions, rate limits, pagination, or output format. The behavioral transparency is minimal.

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: a single Korean sentence stating the purpose, followed by a clear bulleted list of arguments with format and optionality. No unnecessary words, well-organized, and 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?

Given the tool has 3 parameters and no output schema, the description covers the basic purpose and parameter formats. However, it does not describe the return value structure or any error conditions, leaving some gaps. It is adequate but not fully complete for a tool in a complex domain.

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 compensates by explaining each parameter: 'corp_code' is an 8-character DART code, 'bgn_de' and 'end_de' are optional dates with YYYYMMDD format. This adds meaning beyond the schema, but it does not explain the parameters' roles (e.g., date range filtering). The description provides format and optionality, making it minimally helpful.

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 key information about creditor bank management procedure start from a major affairs report. It uses a specific verb ('조회합니다' meaning retrieves) and resource ('채권은행 관리절차 개시 주요 정보'). The sibling 'get_creditor_management_suspension' exists, so this tool is distinguished as handling initiation, giving clear differentiation.

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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, when not to use it, or refer to sibling tools. For a tool with many siblings, this omission limits usability.

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 states that the tool queries data, but does not mention if it is read-only, requires authentication, has rate limits, or any side effects. The description is insufficient for a tool with no 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 description is relatively concise, consisting of a few lines with a clear header and structured Args list. It is front-loaded with the main purpose and parameter details, without unnecessary fluff.

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 lacks an output schema, so the description should explain the return value structure. It does not mention what information is returned, the format, or any pagination. Parameter details are good, but overall completeness is lacking for a query 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?

The description provides meaningful explanations for all three parameters, including the format for corp_code (8-digit company code) and date parameters (YYYYMMDD, optional). This adds significant value beyond the input schema, which only has titles. Given 0% schema description coverage, the description compensates well.

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 that the tool queries information about suspension of creditor bank management procedures from a major issues report. The verb '조회' (query) and specific resource are identified, distinguishing it from siblings like 'get_creditor_management' which likely deals with active management.

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 guidance is provided on when to use this tool versus alternatives, or when not to use it. The description only explains what it does without contextual usage advice.

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 exist, and the description does not disclose behavioral traits such as idempotency, rate limits, authentication requirements, or data freshness. The description only states what the tool does, not how it behaves.

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, using a single sentence for purpose followed by a parameter list. It is front-loaded and direct, with no wasted words.

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 absence of an output schema and 0% schema description coverage, the description is incomplete. It does not mention return values, pagination, error handling, or provide examples, which are important for a financial data retrieval 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?

The schema description coverage is 0%, so the description must compensate. It lists three parameters with brief explanations: corp_code (required, 8-digit), bgn_de (start date), end_de (end date) with format YYYYMMDD. While this adds some value, it does not explain behavior when dates are omitted or other constraints.

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 that the tool retrieves key information from debt securities registration statements (e.g., corporate bonds). It uses a specific verb ('조회합니다') and resource, distinguishing it from sibling tools that cover other securities or reports.

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 guidance is provided on when to use this tool versus alternatives. With many sibling tools for different securities and reports, the description offers no context for selection.

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 provided. The description implies a read operation but does not disclose any behavioral traits such as rate limits, authentication needs, or side effects.

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 sentences: one for purpose, one for parameters. Concise and front-loaded, though the parameter list could be more structured (e.g., bullets).

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?

Parameter definitions are complete, but no return value description or behavioral information. For a tool with many siblings and no output schema, more completeness is needed.

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 0% schema coverage, the description fully explains each parameter with format and examples, adding necessary meaning beyond 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 it queries the outstanding balance of conditional capital securities, using a specific verb and resource. It generally distinguishes from siblings, though a sibling 'get_debt_securities' exists which could be confused.

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 guidance on when to use this tool versus alternatives. Lacks context on prerequisites or scenarios.

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, and the description does not disclose behavioral traits such as read-only nature, rate limits, authentication needs, or what constitutes 'key information'. While 'retrieves' implies read-only, this is not explicit.

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, with a clear purpose statement followed by parameter details. However, the parameter list largely repeats schema information, reducing efficiency.

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 lack of output schema and annotations, the description is incomplete. It does not mention return structure, limitations, pagination, or error handling. Users are left to guess the response format.

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 description adds format details for parameters: corp_code (8-digit required), bgn_de (start date YYYYMMDD), end_de (end date YYYYMMDD). This adds value beyond the schema, which lacks descriptions (0% coverage), but does not provide comprehensive semantics like valid ranges or examples.

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 key information of depositary receipts securities registration statements, using a specific verb (retrieves) and resource (depositary receipts security statements). It is distinct from all sibling tools as no other tool mentions depositary receipts.

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 does not provide any guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. Usage is implied solely by the tool's unique purpose.

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?

Describes key behaviors: returns main text without doc_name, attachments in documents list, and ability to fetch specific attachment. Lacks details on error handling or return format, but with no annotations, provides substantial transparency.

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?

Concise and well-structured: first sentence states purpose, second explains attachment behavior, third provides parameter details in a bulleted list. No redundant 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?

Covers main usage and attachment workflow adequately, but lacks output schema or explicit return format description; still sufficient given parameter count and sibling differentiation.

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?

Given 0% schema description coverage, the description adds full semantic meaning: rcept_no as 14-digit required receipt number, doc_name as optional filename from documents list, with default behavior clearly explained.

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 original text of disclosure documents by receipt number, and distinguishes from sibling tools (which are for specific data types) by focusing on raw document content and attachment workflow.

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?

Clearly explains when to use (fetch document by receipt number, with optional attachment selection) and provides a workflow (call without doc_name for main text, then use doc_name for attachments), but does not explicitly mention when not to use or alternatives.

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 fully disclose behavioral traits. It only states it performs an inquiry, but does not specify read-only nature, auth requirements, rate limits, or error handling. For a simple retrieval tool, this is insufficient transparency.

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: one clear sentence stating the purpose, followed by a bulleted list of parameters. Every sentence adds value, and the structure is efficient with no wasted words.

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 having no output schema, the description does not specify the structure or content of the returned report. It only mentions '주요 정보' (major information). Given the complexity of financial reports and the large number of sibling tools, more detail on output fields or typical usage would improve completeness.

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?

Despite 0% schema description coverage, the tool description explains each parameter: corp_code is an 8-digit DART code, bgn_de and end_de are dates in YYYYMMDD format and optional. This adds valuable meaning beyond the schema, compensating for the lack of schema descriptions.

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 information about dissolution reason occurrence from the major matters report. It uses a specific verb ('조회합니다') and resource ('해산사유 발생 - 주요사항보고서'), making the purpose unambiguous. The name itself is descriptive, and the description adds context that differentiates it from sibling tools that handle other report types.

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 provides no guidance on when to use this tool versus alternatives. While the purpose is clear, there is no mention of prerequisites, exclusion criteria, or links to sibling tools. An agent would have to infer usage solely from the tool name and context.

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 only states that the tool retrieves information, implying a read-only operation, but does not disclose other behavioral traits such as idempotency, rate limits, or data freshness. The lack of such details is a significant 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?

The description is concise, with a one-line purpose followed by parameter explanations. It is front-loaded with the main purpose. However, the parameter list format is a bit informal (using 'Args:' marker) and could be streamlined.

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 lack of output schema, the description fails to explain what the tool returns or its structure. For a tool with three required parameters and no annotations, the description does not cover return format or any prerequisites (e.g., must have valid DART codes). This is a notable omission.

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 description adds meaningful explanations for all three parameters (corp_code, bsns_year, reprt_code), including the 8-digit format for corp_code and example values for reprt_code. Since the input schema has 0% coverage, this compensation is valuable, though the explanations are in Korean and could be more detailed.

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 that the tool retrieves cash and stock dividend information from DART. The verb '조회합니다' (retrieves) and resource 'dividend info' are specific. While it distinguishes from siblings in the financial domain, it could be more explicit about the scope (e.g., 'for a given company, year, and report type').

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 guidance is provided on when to use this tool versus alternatives. The description does not mention any context where this tool is preferred or any exclusions. With many sibling tools, explicit usage guidance is absent.

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 fails to disclose any behavioral traits such as side effects, permissions, or rate limits. While the tool appears to be read-only, this is not explicitly stated.

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 brief but contains redundancy: the English args list largely mirrors the input schema. It is front-loaded with the Korean purpose, but the structure could be improved by integrating parameter descriptions more naturally.

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 schema has 0% description coverage and no output schema, the description should provide more context about expected results and usage. It lacks information about return format, typical use cases, or how the data relates to other corporate actions.

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 description adds meaning to parameters beyond the schema by providing format hints (e.g., '8자리' for corp_code, 'YYYYMMDD' for dates). However, it does not explain the purpose of date range parameters (e.g., reporting period) nor covers the optionality semantics.

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 'company division decision' information from a major matters report, specifying the resource and action. While it distinguishes from siblings by naming the specific decision type, it does not contrast with similar tools like 'get_merger_decision'.

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 guidance on when to use this tool versus alternatives. The description does not mention prerequisites, exclusions, or context for using this specific tool among many similar corporate event tools.

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, and the description only says 'queries information' without disclosing behavioral traits like read-only nature, side effects, authentication needs, or rate limits. For a get tool, basic safety info is missing.

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 short and front-loaded with the purpose. The argument list is clear. Minor improvement could be better formatting, but no wasted words.

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 output schema and no annotations, the description lacks completeness: it does not describe the output format, pagination, or any constraints. For a tool with many siblings, more context is needed.

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 has 0% description coverage, but the tool description provides meaningful parameter explanations: corp_code format (8-digit DART code), bgn_de/end_de format (YYYYMMDD) and optionality. This adds significant value beyond 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 it queries 'division merger decision' information from major reports. The verb '조회' (query) and resource are specific. However, it does not differentiate from sibling tools like get_division_decision or get_merger_decision, which are closely related.

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 provides no guidance on when to use this tool over alternatives. It lacks context for when-not to use it or any prerequisites.

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 for behavioral disclosure. However, it only describes the basic function without mentioning side effects, rate limits, pagination, or data freshness. It does not specify if the operation is read-only or if any state changes occur.

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 short and front-loaded with the purpose. The parameter list is structured clearly with labels. However, the mix of Korean and English might reduce readability for some.

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 output schema and no annotations, the description adequately covers the tool's intent and parameter formats. However, it lacks information about return values, error handling, or any limitations, which could be important for an agent to use 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?

The description explicitly states the format (8-digit for corp_code, YYYYMMDD for dates) and requirement (corp_code is 필수, i.e., required). This adds significant value beyond the schema, which has no parameter descriptions and only titles.

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 retrieves key information on division-related securities reports (분할 관련 증권신고서 주요 정보를 조회합니다). This verb-resource pair is specific and distinguishes it from siblings like get_division_decision which deals with decisions.

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 provides no guidance on when to use this tool versus alternatives. There is no mention of use cases, prerequisites, or exclusions relative to sibling tools.

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 provided, and the description does not disclose any behavioral traits such as read-only nature, required permissions, side effects, or data freshness. It only states what data is retrieved.

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 with a one-line summary followed by clear parameter documentation. It is well-structured and front-loaded with the purpose, though the parameter section could be integrated more seamlessly.

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 explains the purpose and parameters but lacks information about the return value format or structure. With no output schema, the agent may need more details about the response.

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?

Despite 0% schema description coverage, the description thoroughly explains each parameter: corp_code (8-digit DART code), bsns_year (YYYY format), reprt_code (specific report codes). This adds significant meaning beyond 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 retrieves employee status (employee count, average salary), using a specific verb (조회합니다) and resource (직원 현황). It effectively distinguishes from siblings like executive compensation tools.

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 guidance on when to use this tool versus alternatives among the many sibling tools. No mention of context, prerequisites, or exclusions.

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, and the description does not disclose behavioral traits such as destructive nature, authentication requirements, rate limits, or output format. It only describes parameters.

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 with a one-line purpose followed by an Args list. It is front-loaded and efficient, though the Korean language in the purpose line may be less accessible to an English-speaking AI.

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 3 parameters, no output schema, and no annotations, the description lacks completeness. It does not describe the output, limitations, or how it fits with sibling tools, making it insufficient for confident selection.

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 0%, but the description explains each parameter: corp_code as an 8-digit DART code, and bgn_de/end_de as optional dates in YYYYMMDD format. This adds meaning beyond the schema, though it could be more explicit about the date range's role.

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 retrieves information on decisions to acquire equity and investment certificates of other corporations. However, among many sibling tools dealing with equity (e.g., get_equity_investment_transfer, get_equity_securities_acquisition), it does not distinguish itself.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or exclusions.

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, and the description only states it 'retrieves' information, implying read-only but not explicitly. There is no disclosure of behavioral traits such as authentication requirements, rate limits, or error handling.

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 short and front-loaded with the purpose. The Args section is structured. However, the first line repeats the tool name unnecessarily, slightly reducing conciseness.

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 description of return values, the agent lacks information on what data is returned or how to interpret results. For a tool with 3 parameters and many siblings, this is insufficient.

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 description adds basic semantics for parameters beyond the schema (e.g., corp_code is a DART corporate code, dates are in YYYYMMDD format). However, it does not specify what the dates represent (e.g., transfer decision date, filing date), leaving ambiguity.

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 that the tool retrieves key information on transfer decisions of equity and investment certificates from major matters reports, using a specific verb '조회합니다' (retrieves). This distinguishes it from siblings like get_equity_investment_acquisition (acquisition) and get_equity_securities_transfer (securities transfer).

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 guidance is provided on when to use this tool versus alternatives. Given the large number of similar sibling tools, explicit when-to-use or when-not-to-use instructions are missing.

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 provided. Description does not mention read-only nature, data freshness, permissions, or any side effects. Minimal behavioral context beyond the name 'get'.

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?

Concise description with clear section for arguments. No unnecessary text. 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?

Covers purpose and parameters adequately. However, lacks information about the return format or any response structure. With no output schema, a brief note on what to expect in the result would be helpful.

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?

Description fully explains each parameter: corp_code (required, format), bgn_de and end_de (date range). Schema has no descriptions, so the free-text Args section is essential and well done.

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?

Clearly states it retrieves equity securities registration statement main info, including stock issuance and public offering. Distinguishes from sibling tools like get_equity_securities_acquisition by focusing on the registration statement itself.

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 guidance on when to use this tool versus other equity securities tools. Does not mention any prerequisites or exclusion criteria. With many siblings, explicit usage context would help.

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 provided, so description carries full burden. Only states it retrieves information, with no mention of side effects, authentication needs, rate limits, or any behavioral constraints.

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 short and front-loaded with the main purpose, followed by parameter details. However, it mixes Korean and English, which is acceptable but not ideal. Every sentence serves a purpose.

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 should mention return values or pagination. It covers parameters well but omits any description of the response format. Adequate for a simple query but not fully 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?

Despite 0% schema coverage, the Args section explains each parameter's meaning and format (corp_code: 8-digit DART code; bgn_de/end_de: YYYYMMDD, optional). This adds significant value beyond 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 retrieves information on decisions to acquire bonds related to equity securities (주권 관련 사채권 양수 결정). The verb '조회' indicates querying. However, it does not differentiate from sibling tools like get_equity_securities_transfer or get_equity_securities.

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 guidance on when to use this tool versus similar siblings. The description only states what it does, not when to choose it over alternatives like get_equity_securities or get_business_acquisition.

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 fully convey behavioral traits. It only states 'retrieves info' without disclosing side effects, authentication needs, rate limits, or return format. This is insufficient for a safe invocation.

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: a single sentence of purpose followed by an Args list. No unnecessary words. Front-loaded with the core action, making it quick to parse.

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 lack of output schema, the description does not explain what the result looks like, nor does it mention pagination, errors, or data freshness. For a retrieval tool, this is an information gap, though the parameter formats are well-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 0%, so the description bears full responsibility. It adds value by specifying that corp_code is an 8-digit DART company code and that dates are in YYYYMMDD format with optional bgn_de and end_de. This clarifies meaning beyond the bare 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?

Description states it retrieves key information on transfer decisions of equity-related bonds, which clearly distinguishes it from siblings like get_equity_securities or get_equity_securities_acquisition. The verb '조회합니다' (retrieves) and specific resource 'transfer decisions' provide clear purpose, though the Korean phrasing may reduce clarity for an English-centric agent.

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 guidance on when to use this tool versus alternatives. With many sibling tools covering equity-related topics, the absence of usage context or exclusions leaves the agent to infer from the name alone.

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, and the description fails to disclose behavioral traits such as idempotency, rate limits, data freshness, or side effects. As a query tool, it likely is read-only, but this is not stated. The description adds no behavioral context beyond the basic function.

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 (two sentences plus an Args list) and front-loaded with the Korean summary. The structure is clear and easy to parse. No unnecessary information. Could be slightly more efficient by integrating parameter descriptions into the summary.

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 has 3 parameters (1 required) and no output schema, the description covers the purpose and parameter formats but lacks use cases, return value description, or error handling. An agent might not know what to expect from the response or how to handle missing optional parameters.

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 description provides parameter names and brief format hints (e.g., '8자리' for corp_code, 'YYYYMMDD' for dates), which adds value given 0% schema coverage. However, it does not explain the semantics or constraints (e.g., corp_code must be a valid DART code, date range bounds). The effort is adequate but minimal.

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 exchangeable bond issuance decision information, specifying the source (major matter report). It uses a specific verb '조회합니다' (queries) and resource '교환사채권 발행결정' (exchangeable bond issuance decision). However, it does not differentiate from sibling tools like get_convertible_bond or get_bond_issuance, which could cause confusion.

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 guidance on when to use this tool versus alternatives. The description does not mention prerequisites, limitations, or preferred use cases. It implicitly expects the agent to know when exchangeable bond data is relevant, which is insufficient.

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. The description indicates a read-only operation ('조회'), but lacks information on authentication, rate limits, data freshness, error handling, or output behavior. For a tool with zero annotations, this leaves significant 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?

The description is brief and front-loaded with the purpose. The Args list is structured and uses a code-block style for readability. Every sentence is essential; no filler 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?

Given no annotations, no output schema, and 3 required parameters, the description covers purpose and parameter details well. However, it lacks information about the output structure (what data is returned) and any prerequisites (e.g., needing the DART code). This minor gap prevents a perfect score.

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 has 0% coverage, but the description's Args section provides full details: corp_code as 8-character DART code, bsns_year as YYYY format, reprt_code with example values (e.g., '11011' for annual report). This fully compensates for the missing schema descriptions, making parameter usage clear.

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 explicitly states the tool's purpose: to query total compensation of directors/auditors (amount approved at general meeting). The verb '조회합니다' (inquiry) and specific resource '이사·감사 전체 보수현황 (주총승인금액)' clearly distinguish it from other compensation tools listed as siblings, such as individual or type-based compensation tools.

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 guidance on when to use this tool versus siblings like get_executive_compensation_individual or get_executive_compensation_total. The description implies its scope through the '주총승인금액' (general meeting approved amount) qualifier, but without direct comparisons or alternatives, clarity is only moderate.

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 full burden but only states the basic operation. It does not disclose behaviors such as error handling, data limits, authentication needs, or what happens if no data is found.

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 remarkably concise: one line for purpose followed by parameter details. No superfluous information, all sentences earn their 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?

Given the complexity of a tool within a large family of similar executive compensation tools, the description lacks distinguishing features, return format, pagination, or error handling. It is incomplete for an AI agent to confidently select this 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 0%, but the description adds meaning by explaining each parameter (corp_code, bsns_year, reprt_code) with examples and format. It does not cover possible values for reprt_code beyond examples.

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 individual compensation status for directors/auditors over 500 million won, specifying the action and resource. However, it does not differentiate from similar sibling tools like get_individual_pay_over5 or get_executive_compensation_individual_v2.

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 guidance is provided on when to use this tool versus alternatives. The description gives parameter formats but lacks context about suitable scenarios or exclusions.

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 provided, so description carries full burden. It only states it retrieves data (read operation), but omits any behavioral traits like authentication needs, rate limits, or whether modifications are possible. For a financial data tool, more transparency is needed.

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 one sentence followed by a parameter list, with no extraneous information. It is front-loaded with the purpose and concise, earning 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?

Given the complexity (many sibling financial tools, no output schema), the description provides basic functionality but lacks output format, pagination, data freshness, or limitations. 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 0%, so description compensates with parameter descriptions: corp_code (8-digit unique number), bsns_year (YYYY), reprt_code (with example report codes). This adds meaning beyond schema titles, though reprt_code could include more explanation of values.

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 retrieves individual compensation data for directors/auditors with compensation over 500 million won, using version 2.0. The verb '조회' (retrieve) and resource '이사·감사 개인별 보수현황' are specific. However, it does not differentiate from sibling tools like get_executive_compensation_individual or get_individual_pay_over5, which may have similar scope.

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 guidance on when to use this tool versus alternatives such as get_executive_compensation_individual or get_executive_compensation_total. Missing context on prerequisites, data coverage, or reporting periods.

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 fully disclose behavioral traits. It only states the query purpose without explicitly confirming read-only nature, or mentioning any side effects, security, or rate limits. The description is minimal for a query tool.

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 well-structured: one line for purpose, then a clear Args section. Every sentence adds value, and the critical information 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?

Given the tool's simplicity (3 parameters, no output schema, no annotations), the description is adequate for basic usage. However, it lacks any description of the output format or data structure, which would be helpful for an agent to interpret results.

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 0% schema description coverage, the description compensates well by defining each parameter: corp_code as an 8-digit DART code, bsns_year as YYYY format, and reprt_code with example values ('11011' for annual report, etc.). This adds meaningful context beyond the bare 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 states the tool's purpose clearly: '이사·감사 전체의 보수현황을 조회합니다' (queries the total compensation of all directors and auditors). This specific verb and resource distinguish it from sibling tools like get_executive_compensation_individual and get_executive_compensation_type.

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 provides no guidance on when to use this tool compared to alternatives. It only describes the parameters, leaving the agent without context for proper selection among many executive compensation tools.

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 provided, and the description does not disclose behavioral traits such as read-only nature, return data structure, or any side effects. The minimal description fails to compensate for the lack of 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 description is very concise: one sentence outlining the purpose, followed by a clear parameter list. It is front-loaded and wastes no words.

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 has 3 required parameters, no output schema, and numerous similar siblings, the description lacks context on expected output, use cases, or how it differs from related tools. It feels incomplete for an effective agent invocation.

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%, but the description explicitly explains the meaning and format of each parameter (corp_code, bsns_year, reprt_code), adding significant value beyond the schema titles.

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 executive compensation by type (유형별), using a specific verb and resource. However, it does not explicitly differentiate from sibling tools like get_executive_compensation_total or get_executive_compensation_individual.

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 guidance on when to use this tool versus alternatives. The description only provides parameter details, leaving the agent to infer usage context 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.

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

No annotations are provided, so the description must carry the full burden. It discloses the tool is a query (fetches data) but does not mention any behavioral aspects like required permissions, rate limits, pagination, or whether data is historical. The description is too minimal to ensure safe invocation.

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 short and to the point, with a clear purpose line and three parameter lines. It avoids unnecessary text and is easily scannable. Could be improved by using bullet points for parameters, but overall very concise.

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 has 3 required parameters and no output schema, the description should provide more context about what the response contains, any constraints (e.g., only for Korean public companies), and how this tool differs from similar ones. Incomplete for a complex domain.

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 has 0% description coverage, but the description adds meaning for all three parameters: corp_code explained as DART company 8-digit identifier, bsns_year with format example, and reprt_code with enumerated values. This compensates for the schema's lack of descriptions.

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 registered executive list and compensation ('등기임원 명단 및 보수'). It uses specific Korean terms that match the tool name. However, it does not distinguish itself from sibling tools like get_executive_compensation_* which focus on specific compensation details.

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 guidance is given on when to use this tool versus alternatives. With many sibling tools covering executive compensation (e.g., get_executive_compensation_individual, get_executive_compensation_total), the description should indicate that this tool returns general executive info and compensation, not granular breakdowns.

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, and the description does not disclose behavioral traits beyond the basic purpose. It lacks information on side effects, data sensitivity, or any limitations, placing the full burden on the description which falls short.

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 with two sentences and a parameter listing. Every part is necessary and front-loaded, with no wasted words.

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 no output schema, so the description should ideally hint at what the report contains. While it explains the parameter and basic function, it does not describe the return format or fields, leaving the agent partially informed.

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 description adds meaningful context to the sole parameter 'corp_code', specifying it as an 8-digit DART company number and marking it as required. With 0% schema coverage, this adequately compensates for the lack of schema documentation.

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 an executive and major shareholder ownership report. The verb '조회' (retrieve) and resource (report) are specific, but it does not explicitly differentiate from sibling tools like get_large_holding_report or get_largest_shareholder.

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 guidance is given on when to use this tool versus alternatives. The description only explains what the tool does, without any indication of context or exclusions.

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 full burden for behavioral disclosure. It only states it retrieves information, implying a safe read operation, but does not mention permissions, rate limits, data freshness, error handling, or what happens with invalid inputs. This is insufficient for a mutation-free tool.

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 with a clear two-sentence structure followed by an Args list. It is front-loaded and efficient, with no redundant information. Slight improvement possible by integrating the Args into prose, but overall well-structured.

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 3 parameters and no output schema, the description does not describe the return format, pagination, or error conditions. For a tool with many siblings, additional context about what constitutes 'key information' would be valuable. The description leaves the agent with unanswered operational details.

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 description adds meaning beyond the schema by explaining each parameter: corp_code as DART enterprise number (8 digits), bgn_de and end_de as dates in YYYYMMDD format, optional. This compensates for 0% schema coverage. However, it could include more detail like default behavior or inclusiveness.

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 retrieves key information on free capital increase decisions from a major matters report, using a specific verb (조회합니다). The name 'get_free_capital_increase' aligns with this. It distinguishes from siblings like 'get_paid_capital_increase' but does not explicitly differentiate from similar tools like 'get_paid_free_capital_increase'. The resource is defined precisely.

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 guidance on when to use this tool versus alternatives. With many sibling tools for different financial disclosures, the agent would benefit from context on when to choose this one. The description provides no usage context, such as prerequisites or conditions.

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 must fully disclose behavior. It only states it 'inquires' (read-only), but omits details on pagination, error handling, potential empty results, or required permissions. The agent lacks information about what happens when parameters are invalid.

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: a single purpose sentence followed by a well-structured argument list. No extraneous content; every sentence contributes meaning.

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 purpose and parameters are adequately described, the tool lacks output schema and the description does not specify the structure or format of the return value (e.g., number, list, fields). This incomplete information may hamper correct result interpretation.

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 has 0% description coverage, so the description fully compensates. It explains each parameter's format (corp_code 8 digits, bsns_year YYYY, reprt_code specific report types) with examples, adding critical meaning beyond the schema's bare titles.

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 outstanding balance of hybrid bonds (신종자본증권 미상환 잔액을 조회). It uses a specific verb-resource combination, but does not explicitly differentiate from sibling tools like get_corp_bond_outstanding or get_debt_securities_outstanding.

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 guidance on when to use this tool versus alternatives. Missing context about prerequisites (e.g., obtaining corp_code from get_corp_codes) or report code meanings beyond the provided examples.

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 provided. Description only states it retrieves data, lacking details on behavioral traits like sorting, top 5 logic, or return format. Does not disclose any side effects or access requirements.

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?

Extremely concise: one sentence for purpose, then parameter list. Front-loaded with main action. No unnecessary words.

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?

Missing output description or return structure. No mention of data fields, ordering, or that it returns exactly 5 items. For a retrieval tool, this leaves significant gaps despite good parameter coverage.

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 0% but description compensates by explaining each parameter: corp_code as 8-digit DART code, bsns_year as YYYY, reprt_code with specific report types. Adds significant meaning beyond 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 it retrieves individual pay amounts over 5 hundred million won for top 5 persons. It is specific with verb '조회' and resource, and distinguished from siblings like get_individual_pay_over5_v2 and executive compensation tools.

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 guidance on when to use this tool versus alternatives like other compensation tools. Does not mention when not to use or any prerequisites.

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 correctly identifies the operation as a query ('조회합니다'), indicating it is read-only and non-destructive. However, it does not mention rate limits, authentication requirements, or potential return value biases.

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 (two sentences plus an Args list) and front-loads the purpose. The structure is clear, though the Args section could be formatted as a list for easier readability.

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 covers the tool's purpose and parameters but lacks details about the return format, pagination, or any differences from V1. Given no output schema and the tool's simplicity, it is minimally complete but could be improved.

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 has no descriptions (0% coverage), but the description fully explains all three parameters: corp_code (8-digit DART code), bsns_year (YYYY format), and reprt_code with specific report type codes. This compensates completely for the schema 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?

The description clearly states the tool queries the compensation amount for the top 5 individuals with over 500 million KRW using the latest version (V2). It distinguishes itself from siblings like get_individual_pay_over5 (V1) and get_executive_compensation_individual by specifying the exact scope and version.

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 this is the latest version ('최신 버전'), suggesting it should be preferred over V1, but does not explicitly state when to use this tool versus other executive compensation tools. No alternative tools or exclusion criteria are mentioned.

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, so the description must fully convey behavioral traits. It only states the action and parameters, missing details like read-only nature, authorization requirements, rate limits, or data freshness.

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?

Extremely concise: one line for purpose, then bullet list of parameters with clear explanations. No fluff, front-loaded with the main action.

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 retrieval tool with 3 parameters and no output schema, the description covers inputs adequately. However, it lacks return value information, data scope, and potential limitations, which would be helpful given no annotations.

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%, but the description adds meaning: corp_code as 8-digit DART code, bsns_year as YYYY format, reprt_code with specific codes for report types. This compensates for the schema's lack of descriptions.

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 'investment status in other corporations' (타법인 출자 현황을 조회합니다). This specific verb and resource distinguish it from sibling tools like get_equity_investment_acquisition or get_bond_issuance.

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 guidance on when or when not to use this tool compared to siblings. The purpose is implied by the name and Korean description, but no alternatives or exclusions are provided.

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?

As a read operation, the description implies no destructive behavior. However, without annotations, it does not disclose any potential limitations, permissions, or side effects. It provides basic transparency but lacks detail.

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 with two sentences and a parameter line. Every part is necessary and there is no redundant 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?

With no output schema, the description explains what the report contains (holdings of major shareholders >=5%), but lacks details on the return format or additional fields. It is sufficient for a simple list tool but could be more comprehensive.

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 description adds value by specifying that corp_code is an 8-digit DART company unique number and indicates it is required. Since the input schema has 0% description coverage, this addition is crucial and well-presented.

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 retrieves a large holding report and specifically mentions it shows holdings of major shareholders with 5% or more shares. This distinguishes it from siblings like get_largest_shareholder or get_minority_shareholders.

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 guidance on when to use this tool versus alternatives. The description only states what it does, with no explicit when-to-use or when-not-to-use instructions.

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 states the action (query) without mentioning read-only nature, rate limits, or any side effects. Minimal disclosure beyond the basic 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 extremely concise: a one-line purpose statement followed by parameter definitions in a clear Args block. Every sentence is necessary, and the structure is easy to parse.

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 3 required parameters, no output schema, and no annotations, the description provides adequate context for querying largest shareholder data. It covers what the tool does and what parameters are needed, but it lacks information about the output format or error handling.

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 has 0% description coverage, but the description compensates by defining all three required parameters: corp_code (8-digit DART code), bsns_year (YYYY format), and reprt_code (with examples for report types). This adds significant meaning beyond 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 retrieves largest shareholder status and changes. It uses a specific verb and resource, and among many sibling tools, it distinguishes itself as a basic status inquiry, though it does not explicitly differentiate from related tools like get_largest_shareholder_changes.

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 guidance on when to use this tool versus alternatives. The description does not mention prerequisites, scenarios, or exclusions, leaving the agent to infer usage 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.

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

With no annotations provided, the description carries full burden for behavioral transparency. It only states the action without disclosing traits like idempotency, speed, error behavior, or output format. For a simple query tool, this is insufficient.

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 very short and front-loaded with the Korean purpose, followed by English parameter descriptions. It is concise with no unnecessary words, though the structure could be more organized.

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 no output schema and moderate complexity (3 required params, no enums). The description lacks information about return values, pagination, or error handling. It is not complete enough for an agent to fully understand the tool's usage.

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 has 0% description coverage, but the description's 'Args' section explicitly explains each parameter: corp_code (8-digit DART code), bsns_year (YYYY format), reprt_code (with example values like '11011' for annual report). This adds significant meaning beyond 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's purpose: '최대주주 변동현황을 조회합니다.' (Inquires largest shareholder change status). The verb '조회' and resource '최대주주 변동현황' are specific. However, it does not differentiate from similar siblings like get_largest_shareholder or get_large_holding_report.

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 guidance on when to use this tool versus alternatives. There is no mention of prerequisites, context, or comparison with sibling tools. The description is minimal and does not help the agent decide between similar tools.

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 full burden but only describes parameters. It does not disclose behavioral traits like read-only nature, error handling, or rate 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?

The description is extremely concise with no wasted words. It uses a structured format with clear sections for purpose and arguments.

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 covers the basic purpose and parameters but lacks details on output, error conditions, or expected usage context. It is adequate for a simple tool but not comprehensive.

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?

All three parameters are explained with format and optionality, adding value beyond the schema's minimal information. The descriptions are specific (e.g., 8-digit DART code, date format).

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 queries lawsuit filing/judgment information from the major events report, with a clear verb and resource. It distinguishes itself from sibling tools (e.g., bankruptcy, rehabilitation reports) though it doesn't explicitly differentiate.

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 guidance is provided on when to use this tool versus alternatives, nor any context about prerequisites or limitations.

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. The description only implies a read operation but does not disclose any behavioral traits such as authentication requirements, rate limits, or side effects.

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?

Extremely concise: one sentence for purpose plus three parameter descriptions. No wasted words, front-loaded with the key action.

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 output schema exists, and the description does not specify what the returned data contains (fields, structure). For a retrieval tool, this is a significant gap.

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 description explains each parameter with format (YYYYMMDD) and optionality, and it clarifies that 'corp_code' is an 8-digit DART number. This adds meaning beyond the empty schema descriptions (0% 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 the action (retrieve) and resource (merger decision key information from major disclosure report), and it distinguishes from sibling tools like 'get_division_merger_decision' by specifying the report type.

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 guidance on when to use this tool over alternatives. With many merger-related siblings, some context on when to prefer this one would be helpful.

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 provided, and the description lacks any behavioral traits such as return format, data scope, or side effects. It does not disclose what 'major information' includes or any constraints.

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 short and front-loaded with the purpose. However, it mixes Korean and English, and the Args section is not structured as a clear usage guide.

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 large number of sibling tools and no output schema, the description should explain what 'major information' entails. It lacks completeness for a retrieval tool with 3 parameters.

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 0%, but the description adds minimal value beyond parameter names. It restates that corp_code is 8-digit and required, and bgn_de/end_de are dates, which is already inferable from names.

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 'major information of merger-related securities report,' specifying the action (inquiry) and resource (merger securities). It distinguishes from sibling tools like get_merger_decision and get_division_merger_decision.

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 guidance on when to use this tool versus alternatives. The description only lists parameters without context for selecting this tool over siblings.

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 exist, and the description does not disclose any behavioral traits such as idempotency, side effects, authentication needs, or rate limits. It merely states the action without transparency.

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 (one sentence plus parameter list) and well-structured. It front-loads the purpose and then enumerates parameters clearly. Slight improvement could be uniform formatting of parameter explanations.

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 covers parameter formats and valid values, which is essential given no output schema or annotations. However, it lacks information on the output structure, pagination, error handling, or any behavioral context, making it minimally adequate.

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?

Despite 0% schema coverage, the description adds significant value by explaining each parameter: corp_code is '8자리 DART 기업 고유번호', bsns_year is 'YYYY', and reprt_code lists valid codes with their report types. This compensates well for the schema's lack of descriptions.

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 verb '조회' (query) and resource '소액주주 현황' (minority shareholder status), making the purpose immediately clear. It is distinct from sibling tools that handle other specific reports.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or exclusion criteria, leaving the agent to infer usage independently.

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 indicates a read operation (retrieve) without mentioning safety, idempotency, permissions, or side effects. The constraint of max 100 companies is mentioned in the parameter description but not as tool behavior. Overall, transparency is low.

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: a single sentence overview followed by a structured Args section. No extraneous information, and the most important details (overview and parameter formats) are front-loaded. Every sentence serves a purpose.

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 adequately covers input parameters but fails to describe the output. With no output schema, the agent cannot predict what data the tool returns beyond 'main financial accounts'. Given the complexity of the domain and the lack of output specification, the description is incomplete.

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 0%, so the description's parameter details add significant value. It specifies the format for corp_code (comma-separated, max 100, example), bsns_year (YYYY, example), and reprt_code (specific code mappings with descriptions). This compensates for the lack of schema descriptions, though it doesn't define what each parameter represents fundamentally.

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 'main financial accounts' for multiple companies at once, using the verb '조회' (retrieve/lookup). It distinguishes from sibling tools like get_single_company_account (single company) and get_multi_financial_index (financial index vs. accounts), but 'main financial accounts' is somewhat vague.

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 does not explicitly state when to use this tool versus alternatives. The parameter descriptions imply usage for multiple companies, but there is no guidance on when-not or alternative tools. The context from the tool name and sibling list suggests it's for batch retrieval, but explicit guidelines are missing.

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