KRTools Korean Utilities

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

readOnlyHint=true is consistent with a text-cleaning operation, and the description adds cost context ("Free") and a concrete noise-token example. However, it does not say whether the original title is mutated or a cleaned copy is returned, nor how partial/no matches are handled, so behavioral disclosure beyond the annotation is thin.

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 compact sentences with zero filler: the action and scope come first, the usage context second, and the trailing "Free" costs four characters while conveying cost behavior. Nothing needs trimming.

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?

There is no output schema, so the description should state what comes back (a cleaned title string) and whether unmatched titles pass through unchanged; it says neither. For a simple single-string transform this is a modest gap rather than a blocking one, but it is the one thing an agent still has to guess.

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 schema offers only "type: string", but the description compensates by defining what the single parameter should contain: a Korean marketplace product title with bracketed/starred promo noise. That is meaningful semantic guidance beyond the raw type, though edge cases like mixed-language or already-clean titles are unaddressed.

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?

States a specific verb (strip) plus the exact resource (promo noise from Korean marketplace product titles) and names the marketplaces and noise patterns involved. It is unmistakably distinct from the sibling romanization/validation tools, which do not touch title 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?

"before translation or matching" gives a clear triggering context for when to call it, which is useful. There are no explicit exclusions or named alternative tools, but none of the siblings overlap, so the guidance is sufficient without an explicit "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?

readOnlyHint=true already covers the safety profile, so the description only needs to add context. It does: it discloses the output ordering convention (building number first, then street, district, city) via the example, and states 'Free,' which tells the agent there is no cost gate. It omits failure behavior for malformed or non-road-name input.

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?

One sentence plus one inline example; the verb and scope are front-loaded and the example is embedded rather than appended as filler. Nothing is 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?

For a one-parameter tool with no output schema, the arrow example effectively communicates the return shape and ordering, so an agent can call it confidently. The only gap is error/edge-case behavior for unsupported address types, which is minor here.

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% for the single 'address' parameter, so the description must carry the load — and it does, specifying Hangul input, road-name form, and a literal example value. It still does not say what happens with non-Hangul or non-road-name strings.

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?

States a specific verb (convert) and a tightly scoped resource (Korean road-name address in Hangul) with both direction and output form. The concrete before/after example makes the transformation unambiguous and clearly separates it from generic siblings like romanize_korean or romanize_korean_name.

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?

Names the intended context ('shipping labels / forms'), which tells the agent when this is the right tool. It does not name alternatives or state when-not to use it (e.g., jibun/land-lot addresses or already-romanized input), so it falls short of full routing 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?

Annotations already declare readOnlyHint=true, so safety is covered. The description adds two genuinely useful traits beyond that: 'basic liaison rules' flags a fidelity limitation in the output, and 'Free' discloses cost. It does not say what the return value looks like or how non-Hangul characters are handled.

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?

A single front-loaded sentence with the standard named first and the scope qualifier immediately after; nothing is padded. The trailing one-word 'Free.' is a fragment that reads slightly clipped, though it does carry cost 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 one-parameter, read-only conversion tool this is close to adequate, and annotations cover the safety profile. The notable gap is that no output schema exists and the description never states that the result is a romanized string, nor how mixed-script or punctuation input is treated.

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?

One parameter at 0% schema description coverage, so the description must carry the load. It does convey that the input should be Hangul text, which is meaningful for a romanizer, but says nothing about the single 'text' parameter's format, length, or how non-Hangul content is treated.

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?

States a specific verb and resource ('Revised Romanization of Korean ... for arbitrary Hangul text') and names the standard used. The phrase 'arbitrary Hangul text' implicitly separates it from the sibling romanize_korean_name, though it never names that sibling explicitly.

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?

Usage is only implied: 'arbitrary Hangul text' suggests general text rather than personal names, which nudges an agent toward this tool over romanize_korean_name. There is no explicit when-to-use/when-not statement or named alternative, and no guidance on mixed Hangul/Latin input.

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

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

Annotations only declare readOnlyHint=true, so the description earns credit for disclosing output shape: surname convention mapping, hyphenated given name, and both Western and Korean order. It stays silent on ambiguity (e.g., which romanization variant for an ambiguous syllable) and on behaviour for non-Hangul input.

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?

One dense, front-loaded sentence that leads with the action and immediately constrains the domain. The trailing 'Free.' fragment adds no selection value and the sentence is somewhat overloaded with examples, keeping it just below top marks.

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?

There is no output schema, so the description carries the burden of describing the return value, and it does so adequately via the surname-mapping and ordering conventions. Handling of edge cases such as invalid or non-Hangul input is not covered.

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

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

Schema coverage is 100% for the single 'name' parameter, so baseline is 3. The description adds genuine meaning by specifying Hangul input, illustrating multi-syllable surname handling (남궁), and clarifying that both name orders are produced.

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 verb is specific ('Romanize') and the resource is narrowly scoped to 'a Korean personal name (Hangul)', which separates it from address and product-title siblings. It stops short of naming the neighbouring romanize_korean tool, so the boundary with that sibling is left to inference.

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 phrase 'the way it usually appears in passports/English docs' implies the intended context, but there is no explicit when-to-use statement and no alternative named. With a directly overlapping sibling (romanize_korean) present, the missing routing guidance is a real gap.

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

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

Annotations already cover the safety profile (readOnlyHint=true), and the description adds genuine context: checksum-only semantics, no business-status verification, and free of charge. It stops short of describing the return shape (e.g. what is returned on checksum failure), which is the one remaining behavioral 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?

Two short sentences, front-loaded with the core action and format, followed by the important caveat. No filler or restatement of the title.

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 validator with no output schema, the description covers what it validates, what it returns formatted, and the key limitation. The only missing piece is failure behavior / exact return value, which an agent would have to discover by calling.

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% (a bare untyped string), so the description carries the load — and it does, defining the identifier, its 10-digit length, and its canonical hyphenated form. It could be slightly clearer about whether input should be digits-only or may include hyphens, but '10 digits' resolves most of that ambiguity.

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

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

States a precise verb and resource — validate a South Korean business registration number (사업자등록번호, 10 digits) — and specifies the output formatting (XXX-XX-XXXXX). Nothing overlaps with the romanization/cleanup siblings, so an agent can route to it unambiguously.

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 scopes the tool: 'Checksum only; does not confirm the business is active,' which tells the agent when the result is insufficient for a due-diligence use case. It does not name an alternative tool or state prerequisites, but the siblings are unrelated functions so there is little to disambiguate.

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