lawmadi-os

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

With no annotations, the description carries the full burden of behavioral disclosure. It transparently mentions routing to 60 specialist AI leaders, real-time law.go.kr verification, and bilingual support, going beyond what the schema provides.

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

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

The description is concise, front-loaded, and contains no fluff. Two sentences effectively communicate purpose, routing, verification, and language support.

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 2-parameter schema and no output schema, the description provides sufficient context about what the tool does and returns. It could mention response format or limitations, but overall it is complete enough for a straightforward Q&A 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 input schema already has 100% description coverage for both parameters (query and lang). The description only restates bilingual support and does not add meaningful parameter-level semantics beyond the schema.

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

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

The description clearly states the tool asks a Korean legal question and routes to 60 specialist AI leaders with statute-verified analysis. It is specific about the resource and behavior, though it does not explicitly differentiate itself from sibling tools like ask_expert.

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 is for Korean legal questions and supports Korean and English. It provides clear context but lacks explicit exclusions or guidance on when to prefer sibling tools.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the tool is slower and runs a 'full verification pipeline', which is useful behavioral context, but it omits details about side effects, permissions, or potential failures. This adds some value but not extensive 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 compact two-sentence statement that front-loads the purpose and adds a key comparison with `ask`. Every word earns its place, making it highly concise and 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?

Given the tool's simplicity (2 parameters, no output schema) and the absence of annotations, the description adequately conveys the core differentiation and time cost. However, the meaning of 'full verification pipeline' could be more explicit, leaving slight ambiguity about the exact behavior.

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 covers both parameters (query and lang) with descriptions, achieving 100% schema coverage. The description adds no additional parameter semantics beyond the schema, so the baseline score of 3 is appropriate.

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

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

The description clearly states 'Expert mode legal analysis' and explains it runs the full verification pipeline for a more detailed, deeply-cited answer. This distinguishes it from the sibling `ask` by indicating a more thorough version, giving a specific verb+resource+differentiation.

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

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

It explicitly mentions the alternative `ask` and notes 'Slower than `ask`', providing a clear tradeoff that guides when to use this tool (when a detailed, deeply-cited answer is needed) versus the faster standard `ask`. This satisfies the requirement for explicit 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 provided, the description carries the full burden and does well. It discloses the data source (15 rounds, verified gold-standard answers), the return fields (round, subject, question number, answer, stem, citations, link), and quality (law.go.kr verification). It implies read-only behavior through 'Search', though it doesn't explicitly state side-effect-free behavior.

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-organized sentence that packs in purpose, scope, query types, and return details without redundancy. The use of em dashes and parentheses keeps it readable, and every clause 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?

For a search tool with no output schema, the description covers the query dimensions, the corpus scope, and the return fields comprehensively. It also provides data quality context. The optional filters (limit, round, subject) are documented in the schema, so the description remains complete without over-explaining.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantic examples for the 'q' parameter ('2014도6992', '형법 제310조', keyword) and clarifies the output fields. This goes beyond the schema's simple parameter names and 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 a specific verb-resource pair ('Search the Korean bar exam corpus') and differentiates it from sibling tools like lookup_precedent and lookup_statute by focusing on the exam question database. It also gives precise scope (15 rounds, question counts) making the tool's 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?

The description provides clear usage context by listing the types of queries supported (docket, statute article, keyword) and what the tool returns. It does not explicitly name alternatives or exclusion scenarios, but the specificity of the corpus (bar exam questions) implicitly distinguishes it from general 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?

No annotations are provided, so the description must carry the behavioral burden. It adds useful context about being a 1:1 chat and requiring a leader_id from get_leaders, but it does not mention return format, whether context is retained, 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, front-loaded, no-fluff sentence that conveys the core purpose and prerequisite. Every word contributes.

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 two-parameter tool, the description covers basic invocation. However, with no output schema and overlapping sibling tools like ask and ask_expert, it leaves gaps around expected responses and tool differentiation.

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

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

The schema already describes both parameters thoroughly (leader_id and query). The description adds example IDs and the source tool get_leaders, but this is only slight value beyond the schema coverage.

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

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

Description clearly states 'Chat 1:1 with a specific legal leader', specifying the exact action and target resource. It also references get_leaders, which helps distinguish this tool from the broader ask/ask_expert 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?

It provides clear context: use when you have a leader_id from get_leaders and want a 1:1 chat. However, it does not explicitly state when not to use it versus the sibling tools ask or ask_expert.

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

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

No annotations are provided, so the description must carry the burden. It adds 'Public data, no LLM,' which gives some insight into reliability and operation, but it does not disclose potential failure modes, result formats, or whether multiple lawyers might be returned. For a simple read-only lookup, the disclosure is adequate but not rich.

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, front-loaded with the primary purpose, and every phrase contributes useful information (what it does, how to search, a caveat). No redundancy or fluff.

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

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

For a simple lookup tool with no output schema, the description covers the essentials: purpose, input examples, and data source. It hints at the result being a contact point, which is sufficient for an agent to know what to expect. Minor gap: it doesn't specify whether the result includes names/phone numbers or how errors are handled, but this is not critical for a straightforward 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 100% and both parameters have descriptions, but the description adds value beyond the schema by providing additional region examples ('강원 강릉', '은평구') and clarifying that the region can be a province, city, or township. This helps the agent form correct queries.

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: to find the Ministry of Justice 'village lawyer' assigned to a Korean locality. It provides specific context (free legal-consultation contact point) and differentiates itself from sibling search tools by focusing on a niche lookup.

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

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

The description gives concrete usage instructions: 'Search by province, city or township name' with examples. It clearly implies when to use this tool (whenever a village lawyer is needed), but it does not explicitly name alternatives or exclusions. Still, the context is clear enough for an agent to select this tool appropriately.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It discloses the key behavior that every statute/precedent citation goes through fail-closed law.go.kr verification as in ask. This is a critical behavioral trait not visible in the schema. However, it does not mention output format or failure handling, so not a perfect score.

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 are used, but the first sentence contains a long list of document types. Each piece of information contributes to the purpose and usage. Slightly long but not wasteful. Front-loaded with the main action and examples.

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 complexity (4 params, no output schema), the description explains purpose, citation verification, and a prerequisite. It does not describe return format, but that may be inferred. For a drafting tool, the description is sufficient for an agent to select and invoke the tool correctly, though additional details on output structure would improve completeness.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds minimal meaning beyond schema: 'from the user's facts' maps to context, and 'doc_type' example clarifies usage but doesn't add new semantics. It does not compensate for any missing parameter details because none are missing.

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 uses specific verb 'Draft' with resource 'Korean legal document' and lists multiple document types (complaint, civil petition, etc.). This clearly distinguishes it from sibling tools like ask, lookup, or verify_citations 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?

Provides explicit guidance to use list_document_types first for valid doc_type keys, establishing a prerequisite. Mentions the citation verification behavior linking to ask. Does not explicitly state when not to use this tool, but the context is clear enough for an agent to decide.

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 adds meaningful context: the tool reports status based on the API key in use, provides a top-up link, and is intended as a preemptive check. It implies a read-only operation, though it does not explicitly state safety. The added context exceeds a bare mention but stops short of detailing all edge cases.

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, front-loaded with the essential purpose in the first few words. Every word earns its place, and it avoids unnecessary detail. The sentence structure efficiently communicates purpose, contents, and recommended 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?

This is a simple, parameterless tool with no output schema. The description fully covers its purpose, the context in which to use it, and the value it provides. It is complete for an agent to select and invoke the tool correctly, especially given the clarity of the response content.

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 zero parameters, so the baseline is 4. The description does not need to add parameter semantics, but it does describe the output content (remaining credits, plan, top-up link), which is helpful for understanding what the tool returns. There is no parameter-related gap.

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

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

The description clearly states the tool's purpose: 'Your account status for the API key in use — remaining credits, plan, and a top-up link.' It identifies the specific resource (account status tied to the API key) and the exact information returned. This distinguishes it from all sibling tools, none of which relate to account or billing.

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 the tool: 'Call this before a long run of metered queries so you can purchase in advance instead of hitting an exhausted balance mid-task.' This gives a clear use case, but it does not mention alternatives or exclusions. Since no alternative tool appears relevant, a slight deduction is appropriate.

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

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

Without annotations, the description discloses the enriched contents for each stream (verified statute list, live-checked references, source domains, verified case record), giving users a concrete sense of what the returned record includes, though it stops short of detailing error handling or auth.

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

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

The description is one information-dense sentence, front-loaded with the core purpose, and every clause enumerates a distinct stream's contents 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?

With no output schema, the description adequately describes the expected return for each of the six streams, including the date omission behavior; it lacks only mention of failure modes, which is minor for a fetch 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 covers both params syntactically, but the description adds the crucial mapping between stream enum values and their Korean content titles and inclusion details, making the parameter meaning richer than the bare schema.

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

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

The description immediately identifies a specific action—'Fetch one published daily post in full-record form'—and names all six stream variants with their unique content components, clearly distinguishing this from sibling tools like latest_content or lookup_precedent.

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 the date behavior ('Pass a date, or omit it for the latest post in that stream'), providing clear usage context, though it doesn't explicitly name alternative tools or exclusions.

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

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

With no annotations provided, the description fully discloses behavior: it returns specific components (stem, choices, answer key, reasoning, cited statutes/precedents for MCQ; document type, outline, full answer text for essay/record), enforces a 'One item per call' limit, notes the proprietary corpus and no-bulk-export policy, and states that every citation passed law.go.kr verification. This is rich, beyond-schema context.

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

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

The description is appropriately sized and front-loaded with the core action. It uses clear separators for MCQ vs. essay/record and includes each important constraint without unnecessary fluff. Every sentence contributes to understanding the tool.

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

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

Given the lack of an output schema and annotations, this description is remarkably complete. It enumerates all return components, explains parameter combinations for different exam formats, and discloses limitations (single item, no bulk export) plus data quality verification. No critical information seems missing.

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?

Although the schema already describes all four parameters (100% coverage), the description adds meaningful semantic relationships: it clarifies that `no` is needed for MCQ, `format` for essay/record, and that format defaults to 선택형 when `no` is given. This conditional logic is not explicit in the schema, adding real 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 opens with 'Fetch ONE bar-exam question with its full gold answer,' which is a specific verb and resource. It clearly distinguishes this tool from sibling search tools by emphasizing the singular nature and the full answer 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 clear usage instructions for different formats: 'MCQ (선택형): pass round + subject + no → ...' and 'Essay (사례형) and record-type (기록형): pass round + subject + format → ...'. It also notes the one-item-per-call and no-bulk-export constraints. However, it does not explicitly name alternative tools or state when not to use this tool versus bar_exam_search, so it stops short of a 5.

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 output content (names and specialties) and the size (60+), but it does not mention return format, pagination, authentication, or any side effects. For a simple list operation, this is acceptable but not rich in behavioral detail.

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

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

The description is a single, concise sentence that front-loads the verb 'List' and includes key details (count, resource, fields). It contains no filler or redundant information, making it highly efficient.

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

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

The tool is simple with no parameters, no output schema, and no annotations, so the description is the sole source of information. It sufficiently explains what the tool does and what is returned (names and specialties). While it omits details like response structure or pagination, these are not critical for a straightforward list operation.

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 zero parameters, so there is nothing to describe beyond the schema, which is already 100% covered. The description adds no parameter-specific semantics, but the baseline for 0 params is 4, and the description adequately conveys the scope of the result.

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 action ('List'), the resource ('specialist legal leaders'), and the scope ('all 60+'), along with the included details (names and specialties). This distinguishes it from sibling tools like ask_expert or search, which are for queries and finding specific items.

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 the tool is for getting a complete overview of all leaders, but it does not explicitly state when to use this over alternatives like search or ask_expert. There is no mention of exclusions or comparisons, so guidance is only implied by the phrase 'List all'.

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

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

No annotations are provided, so the description carries the full burden. It discloses the critical behavioral trait of being callable without authentication and lists what the tool returns. While it implies a read-only operation, it does not explicitly state side effects or rate limits, but the provided context is sufficient.

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 with the main purpose front-loaded. Every clause provides distinct, useful information with no filler or 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?

Despite lacking an output schema, the description itemizes the response content comprehensively: sign-up flow, API key issuance, free allowance, prices, credit value, and checkout links. It omits minor details like response format or language handling, but the schema covers the language parameter, and the tool's complexity is low.

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

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

The schema fully describes the 'lang' parameter with an enum and default value, giving 100% coverage. The description adds no parameter-specific details, so the baseline score of 3 applies.

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

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

The description opens with 'How to get access and what it costs,' clearly stating the tool's function. It enumerates specific return content (sign-up flow, API key location, pricing in KRW/USD, credit details) and distinguishes itself from sibling tools like get_account.

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

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

The second sentence explicitly states that an AI agent arriving for the first time should call this tool to learn how to obtain access, providing clear when-to-use guidance. It does not mention when not to use the tool or list alternatives, so a 4 is appropriate.

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

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

No annotations are provided, so the description carries the full burden. It adds behavioral context about the publishing gate (citation verification and live-checking), which is useful. However, it does not disclose return format, pagination, or any preconditions (e.g., authentication), leaving gaps for a read operation.

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

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

The description is concise, starting with the main action and resource, then listing streams and adding a valuable quality-gate note. The list is slightly long but every element is informative, and the second sentence 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?

For a simple tool with two well-documented parameters and no output schema, the description provides sufficient context about what is returned (latest content per stream or blank for each) and the quality guarantee. It does not detail return structure, but the tool is simple enough that this is not a critical gap.

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

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

Schema description coverage is 100% for both parameters ('limit' and 'stream'), so the schema already provides full documentation. The description adds only stream names but doesn't add semantics beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose: retrieving Lawmadi's latest daily legal content, with a specific verb ('Get') and resource (the content streams). It enumerates the specific content types (daily, strategy, tech, news, bar, precedent), which distinguishes it from sibling tools like get_daily_content that may have a narrower scope.

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

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

The description implies clear usage: call this tool to fetch the latest legal content across the listed streams. It does not explicitly mention when not to use it or name alternative tools, but the context is clear enough for an agent to select it over other search-like siblings (e.g., search, lookup_precedent).

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 clearly discloses that this is a read-only listing operation and adds the detail about bilingual labels. There are no hidden behaviors or side effects to disclose for such a simple 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 a single, front-loaded sentence that immediately states the action and resource. Every element (examples, label detail) is informative, with no redundancy or filler.

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

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

For a zero-parameter listing tool with no output schema, the description sufficiently conveys what is returned: a list of document types with Korean and English labels. It provides enough context for an agent to select and invoke the tool without ambiguity.

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 accepts zero parameters, so the schema is trivially 100% covered. The description still adds value by specifying the content of the returned list (Korean and English labels, examples), which goes beyond the empty input 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 uses the specific verb 'List' and identifies the resource as 'legal document types Lawmadi can draft', with concrete examples. This clearly distinguishes it from the sibling generate_document, which creates documents, whereas this merely enumerates available types.

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

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

The context for use is clear: when one needs to know the document types available for drafting. It does not explicitly mention alternatives or exclusions, but the purpose is self-evident for a simple list operation. The lack of explicit when-not-to-use guidance prevents a 5.

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 fully carries the behavioral burden. It discloses that results are deterministic with no LLM/hallucination, lists all returned fields (court, decision date, case name, holding, summary, referenced articles, link), and confirms source verification against law.go.kr.

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?

Three dense, information-rich sentences with no fluff. Every sentence adds meaningful detail: what the tool does, what it returns, and the accepted input formats.

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

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

For a single-parameter lookup with no output schema, the description is remarkably complete. It covers source corpus, verification, returned fields, determinism, and input format flexibility, leaving no critical ambiguity.

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

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

The schema already fully describes the single parameter with an example, achieving 100% coverage. The description adds extra value by showing multiple accepted input formats, including full citations, which goes beyond the schema's basic example.

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

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

The description uses a specific verb ('Look up') and clear resource ('Korean court case by docket number in Lawmadi's verified-asset corpus'). It also differentiates from sibling tools like lookup_statute by specifying 'court case' rather than statute.

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?

Clear context is provided: use this when looking up a Korean court case by docket number, and the deterministic no-hallucination note helps set expectations. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of full 5.

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 states what is returned ('article title, body text and law.go.kr link') and the deterministic nature ('Deterministic — no LLM'), which signals reliability and no hallucinations. It does not mention error handling or side effects, but for a read-only lookup tool, these details are sufficient.

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 plus an example line, with no filler. It front-loads the purpose, includes key details (corpus size, return items, determinism), and ends with practical examples. Every sentence 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?

For a simple single-parameter lookup tool, the description is quite complete: it covers what the tool does, what it returns, and gives input examples. It lacks explicit error-handling information, but that is not essential given the deterministic nature and simple schema. The context is sufficient for an agent to select and invoke the tool correctly.

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

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

The schema already describes the 'reference' parameter and gives one example, achieving 100% coverage. The description adds two more concrete examples ('민법 제750조', '형법 제307조 제1항'), clarifying the expected format beyond the schema. This extra context enhances the parameter semantics.

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

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

The description clearly states the tool's function: 'Look up a Korean statute article in Lawmadi's verified-asset corpus.' It specifies the resource (Korean statute article), the action (look up), and differentiates from siblings like lookup_precedent by using 'statute article' and mentioning the corpus. The return values are also listed, 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?

The description implies when to use the tool by providing example inputs ('민법 제750조', '형법 제307조 제1항') and noting it is deterministic ('no LLM'). This gives clear context for exact statute lookup, but it does not explicitly name alternatives or state when not to use it. Sibling tools like lookup_precedent exist, but no direct contrast 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 are provided, so the description carries the burden of behavioral disclosure. It discloses the output ('Returns matching law topics') but does not mention any other behavioral traits like authentication, rate limits, or whether the search is read-only (though that is implied). The description adds minimal context beyond the operation 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?

The description is a single, focused sentence with no superfluous information. It front-loads the action and resource, then states the output, achieving maximum clarity in minimal words.

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

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

Given the tool's low complexity (2 params, no nested objects), the description covers the source, the search scope, and the output type. However, without an output schema, the return format is vague ('law topics' is ambiguous), which is a minor gap in an otherwise complete description.

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

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

Schema description coverage is 100% (2/2 parameters documented). The description adds no additional meaning beyond the schema, so the baseline score of 3 applies. The example query in the schema provides more parameter-level guidance than the description.

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

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

The description uses the specific verb 'Search' and identifies the resource ('Korean statutes, precedents and legal terms') plus the source ('law.go.kr'), clearly distinguishing it from sibling tools like ask or chat_leader. It conveys both the action and the scope of the search.

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 the tool is for searching legal content, which is distinct from asking questions (ask, ask_expert) or leader-related functions. However, it does not explicitly state when not to use it or mention alternatives, so it provides clear context without exclusions.

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

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

No annotations are provided, so the description must disclose behavior. It mentions the source (law.go.kr) but not return format, pagination, filtering, or limitations, leaving behavioral transparency largely unaddressed.

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

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

The description is one sentence with an em-dash example, front-loaded and concise. 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 search tool with well-documented parameters, the description covers what it searches but omits what the response looks like and any pagination/limits. Minimal but adequate for basic selection; lacking in return details.

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

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

Input schema covers 100% of parameters with descriptions. The tool description adds no extra parameter semantics beyond an example of a query, so baseline score of 3 applies.

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

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

The description clearly states the tool searches official Korean statutory forms and appendix tables from law.go.kr, with a concrete example. This distinguishes it from siblings like search and lookup_statute by the specific resource type.

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

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

The description implies its use for finding exact forms under a given act, providing clear context. It doesn't explicitly state when not to use it or name alternatives, but the context is sufficient.

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 of behavioral disclosure. It only states the high-level action and output type without revealing details such as whether the tool answers the query, potential side effects, or limitations on query topics. The description is too terse to provide meaningful 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, tightly written sentence that opens with the action verb and concisely captures the tool's purpose and input. There is no redundant information or filler, making it highly efficient.

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

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

With one required parameter, no output schema, and no annotations, the description covers the basic function but omits details such as the response format, number of questions generated, and when to prefer this tool over siblings. It is minimally complete but lacks richness for a fully informed 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?

The input schema already provides a full description of the 'query' parameter with 100% coverage. The description adds a slight semantic hint that the query is legal-related, but it does not elaborate on how the parameter is processed or any constraints beyond the schema's max length. Baseline of 3 is appropriate.

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

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

The description clearly states a specific action (generate) and object (follow-up legal questions) with context (for a given query). It distinguishes this tool from siblings like ask or search by focusing on generating questions rather than answering or retrieving.

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 generating follow-up questions, but does not explicitly state when to use this tool over alternatives, such as ask or search, nor does it mention any exclusions or prerequisites. The context is clear enough to infer basic intent, but explicit guidance is missing.

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

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

With no annotations provided, the description takes on full disclosure duty and does it well: it states determinism ('Deterministic, no LLM'), names the reference corpus, and clarifies the critical semantics of 'not_in_corpus' as a manual-check flag rather than proof of fabrication. This prevents a dangerous misinterpretation.

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 compact: a one-sentence purpose, a one-sentence mechanism, a one-sentence return summary, and a caveat. Every sentence contributes, and the important warning is front-loaded near the end with clear formatting.

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

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

The tool is relatively simple (one parameter, no output schema), and the description covers purpose, process, output statuses, source links, and a limiting caveat. It could mention edge cases like empty text, but the provided information is sufficient for an agent to select and invoke the tool confidently.

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 already documents the sole parameter with a description and max length (100% coverage), so the tool description doesn't need to add parameter details. It indirectly clarifies what 'text' contains, but does not go 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 opens with a specific verb ('Fact-check') and a precise resource ('Korean legal citations inside any text'), clearly distinguishing this from sibling lookup tools like lookup_statute and lookup_precedent. It also adds scope ('including text another LLM produced'), which removes ambiguity about input sources.

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 states the use case: extracting and checking citations against Lawmadi's corpus, which implies this is for verification rather than retrieval. Alternative tools are not explicitly named, but the contrast with lookup/retrieval siblings is clear from the description. No exclusions are provided, but the intended context is unambiguous.

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