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

No annotations are provided, so the description carries the full burden. It discloses the snapshot vs. live collection behavior and the associated API calls. It also clarifies that the tool returns aggregated counts and sums. While it does not cover rate limits or auth, the description provides reasonable transparency for a non-destructive 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 relatively concise and uses line breaks to separate sections (purpose, dimensions, output, snapshot behavior, filtering). It front-loads the core functionality. However, it could be slightly more structured or formatted for easier scanning.

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 the return values (counts and sums). It covers the key parameter effects and the snapshot mechanism. However, it does not mention error conditions, pagination behavior for top_n, or what happens if no data exists. Still, it provides sufficient context for basic use.

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 adds significant meaning by listing the dimension values and explaining the use_snapshot parameter's effect. It also mentions the filtering parameters (region, ncs, hire_type, pref) and the top_n parameter implicitly. This compensates well 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 aggregates distributions of ongoing recruitment postings, lists the dimensions (region, ncs, hire_type, etc.), and specifies that it returns 'number of postings' and 'sum of recruitment numbers' per dimension. This distinguishes it from sibling tools like search_recruitments, which focuses on individual postings.

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 indicates it is 'for research/policy use' and explains the behavior of use_snapshot (default true) and the ability to narrow the population with filters. However, it does not explicitly state when not to use this tool or provide direct comparisons with alternatives, though the purpose is clear enough.

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 mentions searching and change tracking but does not disclose the output format, whether it returns diff or aggregated results, authentication needs, or any 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?

The description is a single sentence that is front-loaded and to the point. No wasted words, though additional details could be added without losing 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?

Given no output schema and no parameter descriptions, the description is highly incomplete. It fails to provide enough context for an agent to understand the input requirements and expected output, especially for a tool that compares data across years.

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 does not explain any parameter meaning. The input schema has 0% description coverage, and the description only provides the tool's high-level purpose. There is no clarification on 'query', 'year_a', 'year_b', or 'limit'.

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 searches for the same keyword across handbooks from two years, with a hint of change tracking. It distinguishes itself from the sibling 'search_evaluation_handbook' which likely handles a single year. However, the purpose could be more explicit about the comparison output.

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 vs. alternatives. The sibling tool 'search_evaluation_handbook' is not mentioned, and the description lacks context about usage scenarios beyond 'assist change tracking.'

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 full burden. It does not disclose behavioral traits such as read-only nature, response format, pagination, or rate limits. Only basic behavior is implied.

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?

Very concise, two sentences plus an example. Information is front-loaded with the 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?

Given 5 parameters, no output schema, and no annotations, the description is insufficient. It misses explanation for year_from/year_to, category, and output structure. Also lacks guidance on when to use this vs similar tools like get_institution_metrics.

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 must add meaning. It explains org_codes (list from search_institutions, 2~5 items) and item_query with examples. However, category, year_from, and year_to are not explained in detail.

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 compares 2~5 institutions using the same indicator, with a reference to design document. It distinguishes from siblings implicitly as a comparison tool, but does not 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?

It explains when to use (comparing 2~5 institutions) and provides a hint to use item_query to lighten response. However, it lacks explicit when-not-to-use or alternative 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. Description mentions returning time series and filtered news, but does not disclose whether tool is read-only, required permissions, rate limits, or error handling. Adequate but incomplete.

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 (4 sentences) with front-loaded purpose and example. Every sentence adds value; 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?

Tool has 6 parameters and no output schema. Description explains main function and parameter mapping but does not describe output structure, error handling, or edge cases. Adequate for basic use but leaves 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?

Schema description coverage is 0%. Description adds context for topic (mapping to categories) and institution specification (org_code or query), but does not explain parameter formats, constraints, or possible values for other params like news_days, metric_years, news_limit.

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 cross-checks news claims with public disclosure indicators, gives an example, explains topic-to-metric mapping, and specifies output (time series + filtered news). Distinct from siblings like get_institution_news and get_institution_metrics.

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?

Implies usage for verifying news with data, provides context with example and mapping. Lacks explicit when-not-to-use or alternative tool references, but context is clear enough from sibling list.

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?

Despite no annotations, the description reveals key behaviors: automatic classification into 8 themes, output includes counts, representative headlines, and a date timeline. It also implies a limitation (works best for institutions with high coverage via '보도량 많은 기관'). No destructive actions are mentioned, fitting 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.

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

The description is well-structured: first sentence states the main action, second details the output, and third provides a use case. It is front-loaded with the core purpose. While slightly verbose with the listed themes, every part earns its place. Could be slightly more concise but overall effective.

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 explains return structure (theme counts, headlines, timeline) sufficiently. It also provides a use case. However, it lacks any explanation of the 5 input parameters, leaving a gap in completeness. The tool has moderate complexity, and the description misses parameter documentation.

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 5 parameters with 0% description coverage—no parameter descriptions are provided in the schema or the main description. The description only indirectly references 'days' via an example ('한 달'), but it does not explain org_code, query, max_fetch, or per_theme. With this low coverage, the description fails to add meaning to 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 function: it automatically classifies and aggregates institution news by theme, returning counts and timelines instead of a flat list. The verb 'digest' and resource 'institution news' are specific, and the description distinguishes it from a flat article list, implying differentiation from sibling tool get_institution_news.

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 contrasts with 'flat article list' and gives an example query ('summarize KAMCO's issues for the past month'), indicating when to use the tool for distribution insights. However, it does not explicitly name alternatives or when not to use it, though the contrast with a sibling tool provides implicit guidance.

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

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

In the absence of annotations, the description effectively discloses key behaviors: mode-dependent sorting, subsidiary handling (exclude_subsidiaries, use_classification_org_type), and a disclaimer that results are a simple sort not a basis for evaluation. However, it does not cover error handling 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?

The description is front-loaded with the purpose, followed by parameter explanations in a structured, bullet-like format. It is relatively efficient but slightly verbose with multiple sentences; overall well-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?

Given 10 parameters, no annotations, and no output schema, the description covers many aspects but has gaps: missing explanation of year_from/year_to behavior, no description of output format beyond 'simple sort', and no mention of error handling. Could be more 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?

With 0% schema description coverage, the description compensates by explaining mode options, item_query examples, and filter parameters (org_type, ministry, exclude_subsidiaries, use_classification_org_type). It adds context for item_query values. Missing explanations for year_from, year_to, and n are partially mitigated by defaults.

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 as condition-based institution screening for top/bottom indicators or growth rates. It specifies three modes (top_n, bottom_n, growth_rate) and distinguishes from sibling tools like search_institutions and get_institution_metrics 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.

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

The description provides details on parameter usage (mode, item_query, filters) but does not explicitly state when to use this tool versus alternatives like search_institutions. It implies usage for ranked screening but lacks direct guidance on exclusions or when not to use.

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 full responsibility for behavioral disclosure. It only states that it retrieves text (a read operation) but does not disclose any potential side effects, authentication requirements, rate limits, or what the response format is. Given no output schema, this 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 extremely concise: one sentence that efficiently conveys the purpose, the resource, and the prerequisite. Every part is necessary and no words are wasted.

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 low complexity (1 parameter, no output schema), the description covers the essential purpose and input. However, it lacks information about the return value (e.g., what format the text is returned in) and error handling for invalid IDs, making it somewhat 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?

The single parameter 'rule_id' has 0% schema description coverage, so the description must compensate. It adds meaning by specifying that rule_id is the 'id' from search_admin_rules results, which is valuable context beyond just the parameter name.

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 (조회/retrieves) and resource (행정규칙 본문/admin rules text). It explicitly distinguishes from sibling tools like get_law_text and get_guideline_text by specifying the type of legal document. The prerequisite dependency on search_admin_rules is also clearly indicated.

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

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

The description explicitly states that the tool requires the 'id' from search_admin_rules results, providing clear context for when to use it. However, it does not explicitly state when not to use it or mention alternatives among 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?

With no annotations, the description should disclose behavioral traits. It does not state it's a read-only operation, what happens on invalid input, or whether results are paginated. Only the basic query operation is hinted.

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

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

The description is extremely concise—two sentences that immediately convey the tool's function with examples. No redundant text.

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 low schema coverage, the description should provide more context such as return format, error handling, and the role of the year parameter. It is insufficient for an agent to reliably use 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%. The description explains the query parameter (indicator name) with examples, but the year parameter is completely ignored, leaving its purpose and usage unclear.

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 detailed evaluation content, scoring, and indicator definitions by indicator name. It gives concrete examples, making purpose evident. However, it does not explicitly differentiate from sibling tools like list_evaluation_indicators.

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, so the description carries the full burden. It states the tool retrieves data (read-only behavior is implied) but does not disclose any other behavioral traits like 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?

The description is a single sentence that front-loads the purpose with a clear verb and resource. Every word is necessary, and no extraneous information is present.

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 (1 parameter, no output schema, no nested objects), the description adequately covers the core functionality. However, it does not mention return format or any pagination, which is acceptable for a simple get-by-ID 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 parameter 'facility_sn' has no description in the input schema (0% coverage). The description adds value by clarifying that it is a facility serial number (시설 일련번호) with alternative names sn/fcltSn, which helps the agent understand the parameter 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 verb 'retrieve', the input (facility serial number), and the output (detailed information and attachment metadata). It distinguishes the tool from siblings like 'search_facilities' by specifying retrieval by a single ID, but does not explicitly contrast with other 'get_*' 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?

The description implies usage when a facility serial number is known, but provides no explicit when-to-use or when-not-to-use guidance compared to sibling tools such as 'search_facilities' for searching or 'get_institution_profile' for institutions.

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 cover behavioral traits. It mentions what is returned (provision text or table of contents), but does not explicitly confirm read-only nature, rate limits, or auth requirements. Basic behavior is covered.

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: first states purpose and prerequisite, second explains conditional behavior. No unnecessary words, efficiently 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?

No output schema, but description clarifies return content. Could mention that it is read-only, but overall adequate given the tool's simplicity and sibling 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 has 0% description coverage, but description adds meaning: doc_id source explained, article example given. Adds value beyond schema which only provides type and title.

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 specifies retrieval of guideline provisions, distinguishing from siblings by requiring doc_id from search_guidelines and explaining output based on article parameter (full text vs. table of contents).

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

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

Explicitly states prerequisite: doc_id from search_guidelines results. Explains behavior with and without article. Does not list when not to use or alternatives, but the sibling context makes it 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?

With no annotations, the description carries full burden for behavioral disclosure. It only says '조회합니다' (queries), implying a read operation, but does not state if it is read-only, whether it has side effects, or any other behavioral traits like 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?

The description is very concise—one sentence containing the main action and endpoint. However, it is too terse and misses critical information that could be included without bloating. Conciseness should not come at the expense of completeness.

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 two parameters, no output schema, and no annotations, the description is inadequate. It does not explain what constitutes a 'branch', the structure of the response, or any edge cases. The agent is left with many unknowns.

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%, and the description does not explain any parameter. It does not clarify what 'org_code' represents or that 'limit' controls the number of branches returned. The schema provides minimal info (default and type), but the description adds no value.

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 a list of branches by institution code, referencing the endpoint '/brnch'. The tool name matches, and it distinguishes from sibling tools like 'get_institution_profile' or 'get_institution_metrics'. However, the description is very brief and lacks any nuance.

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_institution_profile' or 'find_institutions_by_criteria'. The description does not mention any prerequisites, exclusions, or context for use.

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

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

The description lists the components returned but does not explicitly state read-only behavior, rate limits, or any side effects. Since annotations are absent, the description should cover safety but 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?

Description is concise with a clear purpose statement followed by a structured list of returned components. No fluff, but could explicitly parameter mapping.

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 lists return categories and identifies the institution via org_code or query, but fails to explain parameter defaults, behavior when both identifiers are missing, or the format of metrics trends. With no output schema and no annotations, more detail 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 description explains the use of org_code and query, and hints at news recency and count, but does not explicitly map to all five parameters (e.g., metric_years is omitted). With 0% schema coverage, the description should document all parameters.

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 aggregates profile, key metric trends, recent news, and recruitment into a one-shot briefing, and distinguishes it from sibling tools that provide individual pieces of information. Example usage is provided.

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 usage for a comprehensive overview, but does not explicitly contrast with siblings or provide when-not-to-use 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the tool returns time series data, lists available categories, and describes item_query behavior with examples. It does not mention destructive actions, authentication, or rate limits, but since it is a read-only query tool, the description sufficiently conveys the non-destructive nature.

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, front-loading the main purpose and using bullet points for categories. It is informative but slightly lengthy due to detailed examples and Korean text. Every sentence adds value, though some redundancy could be trimmed.

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 5 parameters and no output schema, the description covers the primary use case, explains categories and item_query, and provides an alternative for staff summary. It does not describe the output format or pagination, but for a metrics query tool, the essential context is present.

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 add meaning. It explains category values and item_query usage with concrete examples, but does not fully describe org_code, year_from, or year_to. The defaults for year_from and year_to (0) are not explained, leaving ambiguity about their meaning. The description partially compensates for the lack of schema descriptions but has 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 main purpose: '기관의 공시지표 시계열을 조회합니다.' (query institution disclosure indicator time series). It lists specific categories and explains how item_query works, distinguishing it from the sibling tool get_institution_staff_summary by recommending the latter for a summary of personnel status.

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 explicit guidance on when to use this tool (time series of disclosure metrics) and recommends an alternative (get_institution_staff_summary) for staff summaries. It explains categories and item_query usage, but does not explicitly state when not to use it relative to other siblings like list_metric_categories or list_metric_items.

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 fully discloses key behavioral traits: OR search with aliases, post-fetch date filtering due to API limitations (Naver API lacks date parameter), sorting options, and pagination behavior for max_fetch. Limitations are transparently 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 front-loaded with the main purpose in the first sentence, followed by parameter details in a structured, bullet-like format. Each sentence adds value, though some minor redundancy (e.g., repeating '네이버 API는 기간 파라미터가 없어' could be slightly more concise). Overall well-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?

Given 6 parameters, no annotations, and no output schema, the description provides sufficient context for behavior and limitations. It covers parameter interactions and API dependencies. However, it does not describe the structure of the returned data (e.g., fields like title, url, date), which would be helpful for an agent. Missing this detail reduces completeness slightly.

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 must compensate. It explains 5 of 6 parameters (org_code, query, days, sort, max_fetch) in detail, describing their roles and special behaviors (e.g., alias substitution, date filter mechanism). The 'limit' parameter is not mentioned, but its purpose is standard. Overall, 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 action ('검색합니다' - searches) and the resource ('공공기관 관련 최근 뉴스' - recent news about public institutions). It distinguishes itself from sibling tools like 'digest_institution_news' by focusing on raw news retrieval, with specific details on how it handles org_code and query for institution-specific searches.

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 parameter-level guidance (e.g., when to use org_code vs query alone) but does not address when to choose this tool over alternatives like 'digest_institution_news' or 'cross_check_news_with_metrics'. No explicit 'when not to use' or comparison to siblings is given.

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 the description carries the full burden. It explains the optional detail inclusion but omits behavioral traits like idempotency or side effects. For a read operation, this is adequate but not exceptional.

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 concise sentences, front-loaded with the main action. Every sentence adds value with 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?

For a simple read tool with two parameters, the description covers the core function and optional behavior. The lack of output schema is mitigated by describing what the profile includes (basic info and optional details). Mostly 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?

With 0% schema coverage, the description adds meaning by describing the include_detail parameter's effect. However, the org_code parameter is described using 'instCd' rather than the schema name, which may confuse the agent.

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 a basic profile by institution code, distinguishing it from siblings like get_institution_metrics or get_institution_news. However, it uses 'instCd' for the parameter while the schema uses 'org_code', causing minor ambiguity.

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 usage (retrieve profile) but does not explicitly state when to use this tool over siblings or any prerequisites. The use case is implied by the name and description content.

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 present. Description discloses return of authorized vs actual categories and a specific field note, but lacks details on authentication, rate limits, or behavior with missing parameters. Some transparency but gaps remain.

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 with clear structure, front-loaded with key action. Second sentence adds value but could be more structured. No waste.

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 4 parameters and no output schema or annotations, description lacks parameter explanations, return format, and prerequisites. Usage examples help but incomplete for effective use.

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 for 4 parameters. Description does not explain org_code, query, year_from, or year_to. No parameter semantics added 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?

Description clearly states it summarizes institution staff by distinguishing authorized (정원) vs actual (현원) and gives query examples, differentiating it from sibling tools like get_institution_metrics or get_institution_profile.

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?

Describes when to use (queries about staff count) and provides guidance on interpreting headcount.estimated_total. No explicit exclusion of alternatives, but context is 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 full burden. It describes the behavioral difference between calling with article (returns full text) and without (returns table of contents), and warns about full_text length. However, it does not specify response format, error handling, or what happens with invalid mst/article values.

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, with two paragraphs that front-load the purpose and prerequisite. Every sentence adds value, though the second paragraph is dense with multi-line instructions. Minor improvement could be breaking into bullet points.

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 no annotation, the description lacks details on the return structure (e.g., fields, format). It adequately covers usage patterns and parameter meanings, but the agent may need to infer response format or error behavior, leaving some incompleteness.

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 compensates by explaining mst (law serial number from search_laws), article (specific article number or empty for table of contents), and full_text (set true only if all articles needed). It adds meaning beyond the parameter names and defaults.

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 law articles (법령의 조문) and explicitly links to search_laws via the mst parameter. It distinguishes itself from sibling tools like search_laws, get_admin_rule_text, and get_guideline_text by specifying its unique role in fetching article-level content.

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 explicit step-by-step usage: first use search_laws to get mst, then call get_law_text without article to get the table of contents, then re-query with a specific article. It advises against using full_text=True unnecessarily, offering clear when-to and when-not-to guidance.

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

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

No annotations are provided, so the description carries full burden. It implies a read-only operation but does not explicitly state behavioral traits such as required permissions, rate limits, or side effects. For a simple lookup tool, this is adequate but not fully transparent.

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

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

The description is a single, well-structured sentence that conveys the core functionality without unnecessary words. It is front-loaded with the key information.

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

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

Given that this is a simple tool with one parameter and no output schema or annotations, the description covers the main purpose. However, it could mention that a valid serial number is required or hint at the return structure for 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?

Schema coverage is 0%, so the description must compensate. It explains that the parameter is a serial number (sn/recrutPblntSn) and that it is used to look up the recruitment profile, adding essential context 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 action (조회/retrieve) and the resource (채용공시/recruitment announcement), and specifies that it retrieves details, stages, and attachments. It distinguishes from sibling tools like search_recruitments which is for searching.

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. Sibling tools include search_recruitments for searching and other get tools, but the description does not provide any 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?

Discloses what it checks (API key, local data loading) but no annotations exist. For a read-only status check, this is adequate but could mention it's non-destructive.

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, front-loaded with action, and includes context in second part. Every word earns its place.

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

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

Sufficient for a simple status check with no parameters. Could mention expected output format but not critical given low complexity.

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?

No parameters, so schema coverage is 100%. Description adds no param info, baseline 4 applies.

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

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

Clearly states it checks server status covering API key and local data loading, specifically for pre-demo use. Distinct from sibling tools that focus on data retrieval.

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?

Specifies usage context ('pre-demo check') but doesn't 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?

With no annotations, the description carries the full burden. It discloses the data source and that only_with_metric filters items, but does not mention read-only nature, response format, or pagination. 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 with a clear header, example queries, and parameter explanations. Every sentence adds value, though some parameter details could be more directly aligned.

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 7 parameters and no output schema, the description covers the core functionality well. It provides source context and parameter semantics for the key filters, making it actionable for an AI agent.

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 compensate. It describes disclosure_type, schedule, metric_category, and only_with_metric with usage details, but omits query, group, and limit. Partial 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 states a specific verb ('조회합니다' = query) and resource ('경영공시 50개 항목 카탈로그'), clearly distinguishing it from sibling tools that focus on different aspects like institutions or metrics.

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?

Provides explicit example queries (e.g., '재무 공시는 언제 올라와?', '수시공시 항목만') that illustrate when to use this tool, though it does not explicitly state when not to use or mention 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 carries full burden. It does not disclose behavioral traits such as what happens with default parameter values, data freshness, or any limitations. Only mentions that it retrieves a table.

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. It uses a line-break format for parameter examples, which aids readability. However, the structure could be more formalized.

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, no annotations, and three parameters, the description explains the main purpose and two parameters but omits behavior when parameters are empty, year ranges, and return format. It is moderately complete but has notable 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?

Schema coverage is 0%, and the description explains org_class and org_subtype with examples and a reference to the sibling tool. It does not explain the year parameter or provide value ranges, partially compensating for the missing 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 verb '조회합니다' (retrieves) and resource '유형별 평가지표·배점 표' (evaluation indicators/scores table by type). It distinguishes from siblings such as list_evaluation_org_types and get_evaluation_indicator_detail.

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 suggests using list_evaluation_org_types to check types first, providing implicit usage guidance. However, it lacks explicit when-to-use vs. alternatives or when-not-to-use 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?

No annotations are provided, and the description fails to disclose behavioral traits such as data source details, output format, or any side effects. The tool's behavior is opaque.

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, but it sacrifices completeness. While there is no waste, it lacks essential details about parameters and usage.

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 (1 param, no output schema, no annotations), the description is severely incomplete. It does not explain the year parameter, output format, or any constraints, leaving an agent underinformed.

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 single parameter 'year' has no description in the schema (0% coverage), and the description does not mention or clarify its purpose. No value is added beyond the schema's minimal type information.

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 lists institution types from a handbook, with examples. It identifies the action and resource, though lacks explicit differentiation from sibling tools, which are sufficiently distinct.

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 without providing 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, but the description implies a read-only list operation. It does not explicitly state non-destructive behavior or return format, but for a zero-parameter list tool, the description adequately conveys functionality.

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 two sentences, concise and front-loaded. Every sentence provides essential information without redundancy.

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

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

Given the simplicity (no parameters, no output schema), the description is largely complete. It could mention the output format (e.g., list of strings), but the usage context compensates.

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

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

The tool has no parameters, and the input schema coverage is 100%. The description adds value by explaining that the output serves as category values for other tools, which is useful semantic context 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 explicitly states the tool lists disclosure metric categories, provides examples (staff, salary, finance, welfare, 11 types), and distinguishes itself by noting it provides category parameters for sibling tools get_institution_metrics and compare_institutions.

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 clearly indicates the tool's output is used as the category parameter for two sibling tools, giving direct context for when to use it. It does not explicitly mention when not to use it, but the use case is straightforward and well-defined.

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 fully bears the burden. It discloses that the tool returns item names and filters by org_code if given. However, it does not mention read-only nature, side effects, or other behavioral traits. Behavior is adequately described for a simple 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 three sentences: the first states the core purpose, the second provides a concrete example, and the third explains an optional parameter. It is front-loaded and 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?

Given the simple tool with 3 parameters and no output schema, the description covers the core functionality, explains all parameters, and gives an example. It does not specify return format, but that is acceptable given the lack of output schema. It is nearly complete for the tool's complexity.

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 compensate. It explains 'category' with an example, 'item_query' as a search term, and 'org_code' as a filter for organization-specific items. This adds significant meaning beyond the bare schema, though it could specify the format of item_query (e.g., substring match).

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 metric item names within a category, with an explicit example. It distinguishes from sibling tools like 'list_metric_categories' and 'get_institution_metrics' by focusing on items within a category.

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 an example and explains the effect of org_code, implying usage context. However, it does not explicitly state when to use this tool versus alternatives like 'list_metric_categories' or 'get_institution_metrics', nor are there any when-not-to-use caveats.

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 the description carries full burden. It explains what the tool searches, mentions edge cases (zero results may indicate annual guidelines), and references a resource. It implies read-only behavior but does not explicitly state it or mention auth/rate limits. Still, it provides adequate context for a search 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 informative and front-loads the main purpose. Each sentence adds value, covering purpose, context, alternatives, and follow-up. It is slightly verbose but 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?

No output schema exists, so the description should detail return values. It mentions results have an 'id' field and hints at the resource for admin rules, but lacks full parameter documentation and field details. Adequate but with 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?

Schema description coverage is 0%, so description must compensate. It only implicitly clarifies 'query' as the search keyword. The other parameters (page, display, scope) are not explained, leaving ambiguity about their function and valid 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 the tool searches administrative rules by keyword, identifies the source (National Law Information Center), and distinguishes it from sibling tools like search_guidelines. It uses specific verbs and provides examples, making the purpose unambiguous.

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?

Provides explicit guidance on when to use this tool (for admin rules) and when to use an alternative (search_guidelines if zero results). Also instructs to pass the 'id' to get_admin_rule_text for full text, covering follow-up actions.

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 lacks disclosure of behavioral traits such as read-only nature, side effects, rate limits, or pagination behavior. Only describes the search function itself.

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?

Very concise, front-loaded with main purpose, uses examples and parameter details efficiently with no wasted sentences.

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 4 parameters and no output schema, description covers usage basics but omits return value format, pagination, or ordering, leaving some gaps for a search 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 coverage is 0%, so description adds meaning for query, year, and part with examples. However, limit parameter is not explained beyond default value, and coverage is incomplete.

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 searches the evaluation handbook body by keyword, with examples and filtering options. Distinct from sibling search tools targeting different resources (laws, guidelines, 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?

Examples and parameter usage imply when to use (searching evaluation handbook) and how to narrow results with part/year, but no explicit comparison or when-not-to-use guidance against sibling search 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 the full burden. It discloses the search behavior (unified query across fields), filtering by reservable_only, and pagination response field (has_more). These details add transparency beyond the parameter names, though it does not mention response format 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 concise, using bullet points effectively. It front-loads the purpose and provides essential details in a few sentences without unnecessary fluff. Every sentence contributes meaning, making it easy to parse quickly.

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

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

Given 9 parameters, no output schema, and no annotations, the description is incomplete. It explains only a subset of filtering options (e.g., missing free_only, facility_type_code, region, district) and does not describe the return structure beyond has_more. The agent lacks critical details to fully leverage the tool's filtering capabilities.

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 covers semantics for 4 out of 9 parameters (org_code, query, reservable_only, page implicitly). Parameters like region, district, facility_type_code, free_only, and limit are not explained. Since schema description coverage is 0%, the description adds value but leaves significant gaps for half the parameters.

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 searches facilities managed by public institutions, specifies the use of org_code from search_institutions, and explains the query field's unified search across facility name, institution name, usage method, and address. It effectively distinguishes from sibling tools like search_institutions (institutions) and get_facility_profile (single facility).

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 explicit context by explaining that org_code comes from search_institutions, how filtering with reservable_only works, and pagination instructions via 'has_more'. However, it lacks explicit guidance on when not to use this tool versus alternatives like get_facility_profile for specific facilities.

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

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

With no annotations provided, the description carries the full burden. It discloses that the tool searches local data, operates at clause level, supports AND queries, and references an external resource for the list of loaded items. It does not mention authentication or rate limits, but these are generally expected for a search 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 multiple sentences, each serving a purpose: scope, keyword behavior, year usage, reference resource, and sibling tool prioritization. No unnecessary information, and the core purpose 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?

For a search tool with 4 parameters and no output schema, the description provides sufficient context: what constitutes the data source, how keywords work, year separation, and a fallback to a sibling tool. It could mention the default behavior for optional parameters, but overall it is 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?

Schema description coverage is 0%, so the description must compensate. It adds meaning for `query` (AND condition with spaces) and `year` (separate guidelines by year), but does not explain `issuer` or `limit`. The partial coverage earns a moderate score.

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 locally loaded guidelines at the clause level, with a specific verb 'search' and clear resource scope. It distinguishes itself from the sibling tool `search_admin_rules` by noting that standing guidelines should use that tool instead.

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 clearly states when to use this tool (for guidelines not on law.go.kr) and when not to (for standing guidelines, which should use `search_admin_rules`). It also explains query behavior (AND for multiple keywords) and year filtering.

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 bears full responsibility for behavioral disclosure. It only states the search capability and org_code role, failing to mention if it is read-only, pagination behavior, or any side effects. The minimal information does not sufficiently inform an AI agent about the tool's behavioral traits.

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 concise sentences: first clearly states function and search dimensions, second adds critical context about org_code as entry point. No redundant information, efficient for an AI agent 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 4 optional parameters, no output schema, and no annotations, the description provides basic functionality and the role of org_code but lacks details on return format, error conditions, or pagination. It is minimally adequate for a simple search tool but leaves 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?

Schema description coverage is 0%, so the description must compensate. It maps the three search criteria (name, type, ministry) to likely parameters 'query', 'org_type', 'ministry', adding some meaning. However, it does not explain the 'limit' parameter or provide detailed semantics for each parameter. The contribution is moderate.

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 verb '검색합니다' (search) and resource '공공기관' (public institutions) with search dimensions (name, type, ministry). It also mentions org_code as entry point for other tools. However, it does not differentiate from sibling 'find_institutions_by_criteria', which may have overlapping functionality.

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?

Description implies usage context: search by name/type/ministry, and org_code is a key to other tools. But it lacks explicit guidance on when to use this tool versus alternatives like 'find_institutions_by_criteria' or other search tools. No exclusions or prerequisites are stated.

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

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

Discloses that complex keywords may yield zero results, explains scope parameter meanings (1=title search, 2=content search), and mentions the 'mst' field for chaining with get_law_text. Lacks disclosure on auth or rate limits but adequate given 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?

Single paragraph with line breaks, front-loaded purpose. Each sentence provides useful guidance (searching, scope, chaining). Could be slightly more concise but no waste.

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, description partially compensates with behavioral details and parameter hints. Lacks return format description (except 'mst') and error handling. 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?

Schema has 0% description coverage. Description adds meaning for scope (1=title, 2=content) and implies query is keyword. Page and display not explained but have defaults. Adds moderate value beyond 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 clearly states '법령(법률·대통령령·부령 등)을 키워드로 검색합니다' with specific verb and resource, distinct from sibling tools like search_admin_rules and get_law_text.

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?

Explicit guidance on using alio://related-laws for public institution queries and advice to use single core keywords to avoid zero results, effectively steering 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, and the description only mentions a parameter mapping. It fails to disclose significant behavioral traits such as pagination, authentication needs, or result format.

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 to the point, but it could be expanded to include more useful information without being verbose.

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 5 parameters, no output schema, and no annotations, the description is severely inadequate. It does not explain how to use the parameters effectively or what the tool returns.

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 adds minimal value by clarifying that org_code is instCd. Other parameters (query, service_class, lifecycle, limit) lack any explanation beyond their 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 states it searches for public services of public institutions, which is clear and distinct from sibling search tools like search_institutions and search_laws. However, it does not explicitly differentiate itself from siblings.

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 over alternatives. It does not specify prerequisites, exclusions, or recommended 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, so the description carries full burden. It discloses that query with org name auto-interprets, cancelled notices are excluded by default (with include_cancelled), and use_snapshot reads from a local snapshot. However, it does not disclose if the tool is read-only, auth requirements, rate limits, or what happens with invalid inputs. Moderate 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 a single paragraph but well-structured with clear line breaks for filters and options. It is fairly concise given the number of parameters and conveys essential information without unnecessary verbosity.

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 main search functionality, filter details, sort options, and snapshot feature. However, it lacks descriptions for a few parameters (ongoing_only, work_region_code, limit) and does not explain the return format or output schema. Given the complexity (15 parameters, no output schema), it is somewhat 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 description coverage is 0%, so the description must compensate. It explains many parameters (query, org_code, region, ncs, hire_type, recruit_type, education, pref, closing_within_days, sort, include_cancelled, use_snapshot). However, it does not explain ongoing_only, work_region_code, or limit. Partial coverage, but adds value beyond 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 searches public institution job announcements, and explains the main parameter org_code and query interpretation. It is specific about the resource (recruitments) and verb (search). However, it does not explicitly distinguish from sibling tools like analyze_recruitments, but the purpose is clear enough.

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 usage context for many filters and sort options, and explains the use_snapshot parameter for API limit avoidance. However, it does not mention when to use this tool versus alternatives like analyze_recruitments, nor does it state exclusions or prerequisites.

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