나라장터 입찰 MCP

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

With no annotations, the description carries the behavioral disclosure burden. It explicitly lists what the tool returns: award-rate distribution, frequent winners, average participant count, and recent award list, and it discloses the Pro-only restriction. It does not mention side effects, but the described behavior is clearly a read-style aggregation.

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 dense sentences with no filler. The action, grouping dimensions, return values, and access restriction are all present and front-loaded, making the description easy to scan and act on.

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 with no required parameters and no output schema, the description covers the essential return semantics and the Pro gating, so an agent can call it without guessing. The only gaps are sibling differentiation and enum-value explanation, which are already reflected in other dimensions.

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 75%, so the schema already documents agency, months, and keyword. The description adds the semantic grouping label '업무구분' for category, but it does not explain the meaning of the enum values (cnstwk, servc, thng, frgcpt) or reinforce the months default. This is moderate added value over the schema, not substantial.

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 ('집계한다') on a specific resource ('과거 낙찰 결과') and clearly names the grouping dimensions and output metrics. This makes it easy to distinguish from sibling tools like search_bids, which imply individual bid lookup rather than aggregation.

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 aggregation-focused wording and 'Pro 전용' constraint imply that this tool is for statistical/analytical summaries rather than individual search, but there is no explicit when-to-use guidance or comparison with siblings. An agent has to infer the appropriate context.

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 does a good job by enumerating the six categories of returned data, implying a read-only lookup operation with no side effects. However, it doesn't explicitly state read-only safety, error behavior, or auth/rate considerations — though the return-content enumeration substantially covers what an agent needs 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 compact sentences with zero waste. The purpose ('상세 조회') is front-loaded, followed by a tight enumeration of return content, then a single usage instruction. Every sentence earns its place and the Korean text is economical while being informative.

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 detail-lookup tool with only 2 parameters and 100% schema coverage, the description is quite complete. It lists the return categories, which partially compensates for the absence of an output schema, and explains how to obtain the input. Minor gaps include error handling and the exact response structure, but for this complexity level the coverage is strong.

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 both parameters are already documented in the schema. The description adds genuine value beyond the schema by linking bid_no to search_bids output, which clarifies the provenance and format expectation of the primary parameter. It also reinforces the default nature of bid_seq via the usage instruction.

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 '조회' (lookup) with a clear resource '입찰공고 상세' (bid announcement details), and enumerates the returned content: qualification requirements, schedule, base amount, contract method, attachment links, and change history. This clearly distinguishes it from siblings like search_bids (search) and watch_bids (watching) — an agent can tell which tool to pick without inspecting schemas.

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 a clear usage flow by stating 'search_bids 결과의 공고번호를 넣으면 된다' (input the announcement number from search_bids results), which establishes a sequential workflow: search first, then fetch details. It doesn't explicitly state exclusions or when-not-to-use, but the linkage to search_bids gives adequate contextual guidance for selecting this tool over its siblings.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It adds a meaningful non-obvious behavior: only collected notices are searchable and collection occurs hourly, and it also lists the returned fields. It does not mention pagination or rate limits, but the key freshness/scope caveat is clearly disclosed.

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 and well-ordered: purpose first, then filters, then the data-freshness caveat, then return fields. Every sentence carries useful information with no filler or repetition.

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 an 8-parameter optional search tool with no output schema and no annotations, the description supplies the returned fields and a critical data-freshness caveat, and the schema covers parameter formats. Minor gaps such as result ordering and how filters combine remain, but the definition is largely complete for invoking 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 input schema already documents all 8 parameters with descriptions, so the baseline is 3. The description's filter summary adds a helpful overview and aligns with the schema's enum and price/date fields, but it provides no new parameter-level semantics beyond what the schema already states.

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

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

The description states a clear verb and resource ('나라장터 입찰공고를 검색한다') and enumerates filter dimensions, making the tool's scope obvious. It does not explicitly differentiate itself from sibling tools like get_bid_detail or search_pre_specs, so it falls just short of full sibling distinction.

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?

There is no guidance about when to choose this tool over siblings such as get_bid_detail, watch_bids, or analyze_history. The only context given is the data-freshness caveat that only hourly-collected notices are searchable, but no alternatives or exclusions are mentioned.

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 behavioral burden and discloses the return fields (사전규격등록번호, 품명, 수요기관, 배정예산, 의견 마감일, 연결된 본공고 번호) and the access restriction 'Pro 전용'. Searching is non-destructive by implication, and the output/access details are meaningful, though pagination or result limits are not mentioned.

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 short sentences, each earning its place: action, use case, return fields, and access restriction. The description is front-loaded with the verb and resource, with no 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 five-parameter search tool with no output schema, the description gives enough orientation: what is searched, why it is useful, what fields are returned, and the access requirement. It does not explain parameter combinations or category semantics, but schema descriptions cover most parameter meaning, making the description reasonably complete.

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

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

The input schema description coverage is 80%, so the schema already defines agency, keyword, from_date, and to_date. The tool description adds no parameter-level detail beyond that, and the category enum values (cnstwk, servc, thng, frgcpt) remain unexplained, so the 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 opens with the precise action '사전규격(발주 전 규격 공개)을 검색한다', naming a specific resource and scope and noting it is the pre-main-announcement stage. This differentiates it from the sibling search_bids tool, though it does not explicitly name the alternative, so it stops 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 '본공고 전 단계라 조기 발굴에 유용하다' gives a clear use context: choose this tool when the goal is early discovery before the main announcement. It does not explicitly state when not to use it or mention search_bids as the alternative, but the context is clear enough.

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

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

With no annotations provided, the description carries the burden of disclosing behavior. It explicitly reveals the scheduled daily 08:00 KST matching and email sending, plus the Pro-only restriction. It also indicates that remove deletes and add persists, giving useful non-obvious context beyond the raw schema.

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 dense sentence that front-loads the core purpose, then lists actions, and ends with the key behavioral note and Pro restriction. Every clause adds information; there is 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?

For a 9-parameter multi-action tool with no annotations and no output schema, the description covers the action taxonomy and unique scheduling behavior, but omits parameter-level requirements per action and return expectations for list/matches. This is sufficient for a basic understanding but not complete for correct invocation of all actions, especially 'add' and 'matches'.

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 only 44%, so the description must compensate. It adds some semantic grouping: 'add로 조건+이메일 저장' connects email and condition parameters to the add action, and 'remove로 삭제' implies watch_id use. However, it does not explain the meaning or combination of keyword, region, category, min_price, or max_price, nor how 'matches' relates to parameters, leaving significant gaps given the low 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 states a clear verb and resource: 'manages bid notification conditions' and enumerates the four actions (add, list, remove, matches) with brief effects. This clearly differentiates watch_bids from sibling tools like search_bids or get_bid_detail, which are about searching and retrieving bid data rather than managing alert conditions.

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: when the user needs to set up or manage bid notifications, with the daily email matching behavior noted. However, it does not explicitly contrast with alternatives such as search_bids for one-off searches, nor does it state when not to use this tool. The guidance is implied rather than explicit.

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