파공넷 경공매

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered elsewhere. The description contributes that the content originates from a specific source document and enumerates what the answer contains (definition, formula, non-computation conditions), which is genuine added context. It does not say what happens when a metric name is unrecognized (error vs. nearest match vs. suggestion list), which is the one behavior an agent would most want to know.

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 fragments with zero filler, front-loading the returned content before the examples. Every clause carries information; nothing could be cut without loss.

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 parameter, full schema coverage, and no output schema, the description does the necessary work by telling the agent what the response will contain. The remaining gap is edge-case behavior for unknown or ambiguous metric names, which matters for a lookup tool but is a minor omission at this complexity.

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

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

Schema coverage is 100% and the single parameter already documents that Korean or English metric names are accepted. The description's examples overlap heavily with the schema's own example list (expected_yield, market_ratio), adding little beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 names a specific resource and its return content: metric definitions, formulas, and conditions under which a metric is not produced, sourced from the llms.txt 'metric definitions' original text. The verb is implicit (the tool name 'explain_metric' carries it), but an agent reading this knows exactly what it retrieves. The sibling tools (court/bankruptcy/onbid search) are clearly a different domain, so confusion risk is low even without an explicit contrast.

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?

Usable examples (expected_yield, market_ratio, 실부담) imply the expected query terms, and the 'llms.txt 「지표 정의」 원문' note implies this is the canonical lookup for metric semantics. However, there is no explicit statement of when to call this versus the sibling search tools, nor any prerequisite or exclusion stated.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered. The description adds valuable behavioral context beyond that: it discloses what the response contains and that the original specification and tenant details are reachable via a url, which tells the agent this is a summarized read, not a full document fetch. It does not cover not-found/error behavior, so not a 5.

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?

Front-loaded noun phrase, then a dense enumeration of returned fields, then one short sentence on where deeper detail lives. No filler and no repetition 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?

With no output schema, the description has to describe the return shape, and it does so field by field, which is exactly right for a single-parameter read. A minor gap: nothing about failure modes when the case_id is unknown or when data is 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?

Schema coverage is 100% and the single case_id parameter already documents its format with two concrete examples. The description adds nothing about case_id semantics, so baseline 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?

States a specific verb+resource (one court-auction item's fact summary) and enumerates the returned facts: price, round, date, expected yield with formula inputs, market comparison, takeover deposit, stake sale. That is far more specific than the title. It does not name a sibling, but '물건 1건' implicitly contrasts with the search_* tools that return multiple 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 trailing '명세서 원문·임차인 상세는 url로' implies this tool gives summaries and the url gives full detail, which hints at when to use it. However, it never names search_court or search_onbid as alternatives or states prerequisites (e.g., needing a case_id from a search first). Usage is inferred rather than guided.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond the annotations: it tells the agent that results contain a summary plus URL and no computed values, which sets expectations for the return content. Recency is stated but left undefined ('최근').

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 compact sentence with the resource type front-loaded and no wasted words. It is arguably too terse, but every clause (recency, summary+URL, no calculations) does carry 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?

There are 5 optional parameters and no output schema, and the description hints at the return shape (summary+URL, no calculated values). It omits ordering, the lack of pagination beyond the schema's limit cap, and when the tool should be preferred over search_onbid, leaving the agent with adequate but incomplete guidance.

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 80%, so the schema already explains sido, query, limit, category and max_min_bid_won (including the 10-item cap and the enum). The description adds nothing about parameter meaning, so baseline 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 names a specific verb (검색/search) and a specific resource (법원 파산공매 최근 공고, i.e. court bankruptcy trustee sale announcements), which distinguishes it from the general auction sibling search_onbid. It falls short of 5 only because it never explicitly names the sibling it is not, leaving the agent to infer the boundary.

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?

'최근 공고' implies that this tool covers recent listings only, and '계산값 없음' hints at the scope of the tool. However, the description gives no explicit when-to-use/when-not guidance and never routes the agent to search_onbid or search_court as an alternative.

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 readOnly/idempotent/non-destructive, so the description correctly spends its budget on non-obvious behavior: only the top 3 results carry computed values (예상 수익률, 시세 대비, 인수 여부) while the rest are null, and the output is factual rather than a recommendation. That null-truncation rule is a genuinely load-bearing disclosure an agent would otherwise misread as missing data.

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 sentences with the verb+resource front-loaded, then output shape, then the caveat about non-recommendation. Every sentence carries information; the phrasing is terse but not padded.

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 10 parameters, no output schema, and no required fields, the description does the necessary work of describing the return shape (per-item fields, null behavior for ranks 4+, detail URL as escape hatch). The only omission is that result-set size capping (limit ≤ 10, no pagination) is left entirely to the schema rather than flagged as a truncation caveat.

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 every one of the 10 parameters is already documented, including enums and the limit maximum. The description adds no parameter-level semantics beyond what the schema states, which is the expected baseline-3 outcome here.

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+resource: searching in-progress court-auction listings on 파공넷, and enumerates the fields returned (사건·소재지·최저가·매각기일·유찰 횟수·상세 URL). It is clearly distinguishable from get_court_facts and search_bankruptcy, though search_onbid is never explicitly contrasted, so sibling differentiation is only implicit.

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 implied by the resource ('법원경매 진행 물건 검색'), but there is no explicit when-to-use/when-not guidance and no routing to search_onbid or get_court_facts for detail lookups. The only forward reference is '“url에서 확인”', which is a data-access hint rather than a tool-selection rule.

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 readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds one genuinely useful behavioral fact: results are summaries with URLs and contain no computed values. It does not mention ordering, default result behavior when no filters are given, or what happens on an empty match set.

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 compact sentence that front-loads the resource and ends with the output contract. Nothing is wasted, though the brevity is near the point where it costs 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?

With six optional parameters and no output schema, the description's note on return content (summary + URL, no calculated values) fills the most important gap. It still leaves unstated what happens when all filters are omitted and whether results are ranked, which matters for a zero-required-parameter search.

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 83%, with each parameter (sido, sigungu, query, category, limit, max_min_bid_won) documented in-schema, so the schema carries the burden. The description adds no parameter-level meaning beyond what is already there, which is the expected baseline for high 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?

Names a specific verb and resource (캠코 온비드 공매 진행 물건 검색) and adds what the response contains (요약+URL, 계산값 없음). Siblings are in adjacent domains (search_court, search_bankruptcy) but the description does not explicitly separate this tool from them, so it falls just short of a 5.

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 '계산값 없음' implies a boundary against calculation-type tools such as explain_metric, and the domain (public auction listings) implies when to pick this over court/bankruptcy search. However, there is no explicit when-to-use or when-not-to-use statement naming an alternative.

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