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

With no annotations provided, the description carries full burden for behavioral disclosure. It only states what the tool does (geocoding) without describing how it behaves: no information about accuracy, rate limits, authentication requirements, error handling, or what happens with invalid inputs. For a geocoding tool with zero annotation coverage, this is insufficient.

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

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

The description is extremely concise - a single phrase that efficiently communicates the core functionality. Every word earns its place, and there's no wasted verbiage. The structure is front-loaded with the essential information about what the tool does.

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

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

Given the complexity of geocoding operations (which typically require specific input formats and produce structured outputs), the description is incomplete. With no annotations, no output schema, and a vague input schema, the description doesn't provide enough context for effective use. It doesn't explain what format addresses or coordinates should be in, what coordinate system is used, or what the return values look like.

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 100% description coverage but only documents a generic 'params' object with free-form properties. The description adds no parameter-specific information beyond the schema. Since schema coverage is high, the baseline is 3, but the description doesn't compensate for the schema's vagueness about what specific parameters are needed for geocoding operations.

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 as a bidirectional geocoder for Korean addresses and coordinates. It specifies both forward (address→coordinates) and reverse (coordinates→address) operations, which provides good specificity. However, it doesn't differentiate this tool from potential sibling geocoders, though none are listed among the provided sibling 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 provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, limitations, or context for choosing this geocoder over other tools. While sibling tools exist, none appear to be direct alternatives for geocoding, but the description offers no comparative information.

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 but offers minimal behavioral insight. It mentions functions like 'geocode' and 'validate' but doesn't disclose critical details such as rate limits, authentication needs, data sources, error handling, or whether operations are read-only or mutative. This leaves significant gaps in understanding how the tool behaves.

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

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

The description is very concise—a single phrase listing functions—which is efficient and front-loaded. However, it's arguably too brief, bordering on under-specification, as it sacrifices clarity for brevity by not elaborating on any aspect.

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 apparent complexity (multiple functions, no output schema, no annotations, and a generic parameter object), the description is incomplete. It fails to address how to invoke different operations, what results to expect, or how it integrates with sibling tools, making it inadequate for effective agent use without additional 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?

The input schema has 100% description coverage but only documents a generic 'params' object as free-form, providing no semantic meaning. The description doesn't compensate by explaining what parameters are needed for each function (e.g., what inputs for normalize vs. geocode), leaving parameters effectively undocumented despite 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?

The description lists multiple functions (normalize, parse, validate, geocode, postal lookup) which gives a general sense of purpose, but it's vague about what specific resource or data type it operates on. It doesn't clearly distinguish this tool from its sibling 'k_address_geocoder', which suggests overlapping functionality without clear differentiation.

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

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

No guidance is provided on when to use this tool versus alternatives like 'k_address_geocoder' or other siblings. The description merely lists functions without context about appropriate use cases, prerequisites, or exclusions, leaving the agent to guess based on tool names alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only lists what is validated but doesn't describe how the validation works, what the output looks like, error handling, rate limits, authentication needs, or whether it's read-only or mutative. This leaves significant gaps for a tool with undocumented parameters.

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

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

The description is extremely concise—a single phrase listing three validation targets. It's front-loaded with the core purpose and has zero wasted words, making it efficient for quick 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?

Given the complexity of validation (three different formats), lack of annotations, no output schema, and a generic parameter object, the description is incomplete. It doesn't explain how to structure inputs, what validation rules apply, or what results to expect, leaving too much ambiguity 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?

The schema has 100% description coverage but only documents a generic 'params' object as 'Free-form params object'. The description doesn't add any semantic details about what specific parameters are expected (e.g., formats for BRN, corp registration, phone), leaving parameters effectively undocumented despite the high schema coverage.

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

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

The description clearly states the tool's purpose: validating three specific Korean business identifiers (BRN, corporate registration, phone format). It uses specific verbs ('validate') and resources, though it doesn't explicitly differentiate from sibling tools like 'k_company_lookup' or 'k_privacy_scan' that might have overlapping validation functions.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose this validator over sibling tools like 'k_company_lookup' or 'k_privacy_scan', nor does it specify prerequisites, context, or exclusions for usage.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions retrieving 'company info + status', which implies a read-only operation, but doesn't specify details like data sources, accuracy, rate limits, authentication needs, or error handling. For a lookup tool with no annotation coverage, this leaves significant gaps in understanding its behavior and constraints.

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

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

The description is extremely concise and front-loaded, using a single sentence that efficiently conveys the core functionality. Every word earns its place, with no wasted text, making it easy to scan and understand 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 the tool's complexity (lookup operation with potential data nuances), lack of annotations, no output schema, and vague input schema, the description is incomplete. It doesn't explain what 'company info + status' includes, possible return values, error cases, or integration context. This leaves the agent with insufficient information to use the tool effectively.

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 1 parameter with 100% description coverage, but the schema description ('Free-form params object') is vague. The tool description implies the parameter should be a business registration number, adding semantic meaning beyond the schema. However, it doesn't specify the exact parameter name or format (e.g., string, numeric), so it partially compensates but doesn't fully clarify usage.

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: looking up Korean companies using a business registration number (사업자등록번호) to retrieve company information and status. It specifies the verb 'lookup', the resource 'Korean company', and the key identifier. However, it doesn't explicitly differentiate this from sibling tools like 'k_business_validator' or 'k_public_data', which might offer 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, such as needing a valid business registration number, or compare it to siblings like 'k_business_validator' (which might validate businesses) or 'k_public_data' (which could provide broader public data). Usage is implied by the purpose but not explicitly 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'real-time' and 'history supported' which gives some context about data freshness and temporal scope, but doesn't cover critical aspects like rate limits, authentication requirements, data sources, error handling, or whether this is a read-only operation versus something that triggers calculations.

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 - just one phrase that efficiently communicates the core functionality. However, it's arguably too terse given the complexity implied by supporting multiple data types (exchange rates, base rates, CPI) with historical data. Every word earns its place, but more structure might be beneficial.

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

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

For a tool that appears to provide financial/economic data with historical support and has a parameter (even if poorly documented), the description is insufficient. With no annotations, no output schema, and a generic parameter object, the description should do much more to explain what data is returned, how to filter it, and the tool's operational characteristics.

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 100% description coverage but only documents a generic 'Free-form params object' without specifying what parameters are actually accepted. The description provides no information about parameters at all - it doesn't mention what inputs control the exchange rate pairs, date ranges for history, or which metrics to retrieve. With 1 parameter that's completely undocumented in both schema and description, this is inadequate.

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 provides real-time KRW exchange rates, BOK base rates, and CPI data with historical support. It specifies the resource (KRW exchange rate, BOK base rate, CPI) and scope (real-time + history), though it doesn't explicitly differentiate from sibling tools like k_market_intel or k_public_data which might offer 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?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, limitations, or how it differs from sibling tools like k_market_intel or k_public_data that might offer similar financial or economic data.

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 but provides minimal behavioral information. It mentions the API returns English JSON, which is useful context, but doesn't disclose rate limits, authentication requirements, error behavior, data freshness, or whether this is a read-only operation. For a public API tool with no annotation coverage, this leaves significant behavioral gaps.

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

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

The description is appropriately concise with a single sentence that packs substantial information: domain (Korean public data), scope (exchange rates, holidays, indicators), and output format (English JSON). It's front-loaded with the core purpose and efficiently communicates key aspects without unnecessary verbiage.

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

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

Given the complexity of a general-purpose public data API with multiple data types, no output schema, and no annotations, the description is insufficient. It doesn't explain how to query different data types through the params object, what the response structure looks like, error handling, or limitations. For a tool that appears to be a gateway to multiple data endpoints, more guidance is needed.

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

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

Schema description coverage is 100% with a single 'params' parameter described as 'Free-form params object.' The description doesn't add any parameter-specific information beyond what the schema provides - no examples of what params might contain, no guidance on required vs optional parameters, or how to structure queries for different data types. Baseline 3 is appropriate since the schema does document the parameter.

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 accesses Korean public data APIs and lists specific data types (exchange rates, holidays, indicators) with output format (English JSON). It distinguishes from some siblings like k_address_geocoder or k_company_lookup by specifying public data scope, though it doesn't explicitly differentiate from k_exchange_rate which appears to be a more specialized sibling.

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 about when to use this tool versus alternatives. The description doesn't mention when this general public data tool should be used instead of specialized siblings like k_exchange_rate or k_market_intel, nor does it provide any context about prerequisites, limitations, or appropriate use cases.

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

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

With no annotations, the description carries full burden but provides minimal behavioral insight. It lists data types but doesn't disclose how the tool behaves—e.g., whether it fetches real-time or historical data, requires authentication, has rate limits, or returns structured vs. raw data. This leaves critical operational traits unclear for a financial data 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, efficient phrase listing key domains without redundancy. It's appropriately sized and front-loaded with the core topic ('Korean financial data'), though it could be more structured (e.g., separating data types with commas or bullets). Every word earns its place, but minor improvements in formatting could enhance clarity.

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

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

Given the complexity of financial data tools, no annotations, no output schema, and a free-form parameter, the description is incomplete. It doesn't explain return values, error handling, or usage constraints, leaving significant gaps for an agent to operate effectively. The listed domains are insufficient to compensate for missing behavioral and output 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?

Schema description coverage is 100%, with one parameter ('params') documented as a free-form object. The description adds no parameter-specific semantics beyond implying financial domains, which doesn't clarify how to structure the params object. Baseline 3 is appropriate as the schema handles documentation, but the description fails to compensate with meaningful context for the free-form input.

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 lists domains (Korean financial data, stocks, FX, Kimchi Premium, news) but lacks a specific verb or action. It states what data is available rather than what the tool does (e.g., retrieve, analyze, or monitor). This makes the purpose vague, though it distinguishes from non-financial siblings like address or privacy tools.

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

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

No guidance is provided on when to use this tool versus alternatives. It doesn't mention sibling tools like k_exchange_rate or k_public_data, leaving the agent to guess based on domain overlap. The description implies financial data contexts but offers no explicit usage rules 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 of behavioral disclosure. It states the tool scans URLs and returns a risk score and report, but doesn't cover critical aspects like whether it's read-only or mutative, authentication needs, rate limits, error handling, or what the report format entails. For a tool with no annotations, this leaves significant gaps in understanding its 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 extremely concise and front-loaded, using just one sentence to convey the core functionality. Every word earns its place, with no wasted text, 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 the complexity of a compliance scanner with no annotations, no output schema, and a vague input parameter, the description is incomplete. It doesn't explain the output format (beyond mentioning 'risk score + violations report'), error cases, or how to interpret results. For a tool that likely involves nuanced legal compliance, more context is needed.

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

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

The input schema has 100% description coverage, with a single parameter 'params' described as a 'Free-form params object'. The description doesn't add any meaning beyond this, such as explaining what specific params might be needed (e.g., URL details, scan options). Since schema coverage is high, the baseline is 3, but the description doesn't compensate for the vague schema 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 clearly states the tool's purpose: scanning URLs for Korean PIPA compliance and returning a risk score and violations report. It specifies the verb ('scanner'), resource ('URL'), and output format. However, it doesn't distinguish this tool from its siblings (e.g., k_business_validator, k_company_lookup), which might also involve compliance checks, so it doesn't reach a perfect score.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for PIPA compliance, or compare it to sibling tools like k_business_validator that might handle other types of validation. Usage is implied by the purpose but lacks explicit instructions.

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

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

No annotations are provided, so the description carries full burden. It mentions the output format (English JSON) but doesn't disclose behavioral traits like authentication needs, rate limits, data freshness, error handling, or whether it's read-only or has side effects. The description is minimal and lacks operational 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?

Extremely concise with zero wasted words—a single sentence listing the tool's purpose and key data types. It's front-loaded and efficiently communicates the core functionality without unnecessary elaboration.

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

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

Given no annotations, no output schema, and a generic input schema, the description is incomplete. It doesn't explain how to specify which data type to retrieve (e.g., weather vs. holidays), what the return values look like, or any constraints. For a tool with one parameter that's a free-form object, more guidance is needed.

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

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

Schema description coverage is 100%, with a single 'params' object described as 'Free-form params object'. The description adds no parameter-specific information beyond what the schema provides, such as example parameters for different data types (e.g., date for weather, currency pair for FX). Baseline 3 is appropriate since the schema documents the parameter structure.

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 provides Korean government data in English JSON format and lists specific data types (weather, FX, holidays, transport). It distinguishes itself from some siblings like k_address_geocoder or k_business_validator by focusing on government data, though it overlaps with k_govdata and k_exchange_rate in scope.

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

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

No explicit guidance on when to use this tool versus alternatives like k_govdata or k_exchange_rate. The description implies it's for accessing Korean government data in English JSON, but doesn't specify use cases, prerequisites, or exclusions compared to similar tools.

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