Server Quality Checklist

Tool Scores

• get_company_infoA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly indicates a read-only retrieval (via 'Get') and specifies the output fields, which adds transparency. However, it does not address potential error behavior (e.g., invalid or missing corp_code) or any rate limits, leaving some behavioral ambiguity.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences with no wasted words. It front-loads the primary action and resource, then lists the returned fields, and finally the key requirement. This is appropriately sized and structured for quick agent comprehension.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a single-parameter tool with no output schema, the description is fairly complete: it enumerates the return fields and the required input. It could mention what happens on lookup failure or note the regulatory context of DART, but these are minor gaps given the tool's simplicity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema only specifies the type and pattern for corp_code, with no description. The description compensates by explaining that this is the DART corporation code and that it must be 8 digits, adding semantic meaning beyond the raw schema. It also implicitly ties the parameter to the company profile look-up purpose.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb and resource ('Get company profile from DART') and enumerates the exact data fields returned (name, CEO, registration numbers, etc.). This clearly distinguishes it from siblings like search_disclosures and get_financial_summary, which serve different purposes.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description states the prerequisite ('Requires DART corp_code (8-digit)'), which clearly indicates when to use this tool (when you have a corp_code). However, it does not explicitly mention when not to use it or provide alternatives from the sibling list, making the usage guidance implicit rather than explicit.

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

• search_disclosuresA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the behavioral burden. It discloses the return fields ('receipt numbers, titles, filers, and dates') and available filter dimensions, which goes beyond the tool name. It does not mention pagination behavior or rate limits, but the core read-only search behavior is well described.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, front-loaded with the core purpose, and every sentence adds value. No filler or redundant information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has 7 parameters and no output schema, and the description covers the main filters and return fields. However, it omits pagination details, parameter formats, and explicit guidance on when to prefer siblings or combined use, leaving some gaps for a fully self-sufficient description.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate. It adds meaning for date range (bgn_de/end_de), corp_code, disclosure type (pblntf_ty), and market (corp_cls), but does not mention pagination parameters (page_no, page_count) or explain enum values. It partially compensates for the missing schema descriptions but not fully.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Search') with a clear resource ('Korean company disclosures filed with the FSS') and explicitly lists return fields. This clearly distinguishes it from sibling tools like get_company_info and get_financial_summary, which target different data.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage: use this tool to find disclosures filtered by date, company, type, and market. It provides clear context but does not explicitly mention when not to use it or name alternative sibling tools, so it lacks explicit exclusions.

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

• get_financial_summaryA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It does add context about CFS/OFS and report codes, which helps understand the data scope. However, it does not disclose the response format, pagination, authentication requirements, or any potential limitations. This is a moderate gap for a read-only tool.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two concise sentences, front-loaded with the core purpose. It packs essential information (statement types, report codes) without redundancy or filler. Every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite having no annotations or output schema, the description covers the essential context: what the tool does, the scope, and the meaning of key parameters. It lacks details on return values and error behavior, but for a straightforward data retrieval tool with moderate schema complexity, it is reasonably complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate. It explains the meaning of fs_div (CFS/OFS) and reprt_code (11011=annual, 11012=half-year, 11013=Q1, 11014=Q3), which are the most ambiguous parameters. It also clarifies that corp_code and bsns_year refer to company and year, though formats are already in the schema. 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.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Get full financial statement line items (BS/IS/CIS/CF/SCE) for a company for a given year and report.' The verb 'Get' and resource 'financial statement line items' are specific, and the mention of CFS/OFS and report codes distinguishes it from sibling tools like search_disclosures and get_company_info.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context on when to use the tool: for a specific company, year, and report type, with consolidated or separate statements. It implicitly guides the user to choose this tool when financial statement line items are needed, but it does not explicitly exclude alternatives or mention when not to use it. The context is sufficient for most use cases.

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