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

Thoroughly describes side effects: downloads, extracts ZIPs, deletes original ZIP, stores in specific directory, uses cache, and refresh behavior. Annotations (readOnlyHint: false, openWorldHint: true) are consistent with this mutation 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?

Information-dense paragraph that front-loads the main action. Could be slightly more structured (e.g., bullet points), but every sentence adds value and it's not overly long.

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 fully explains the return (file catalog without text), how to use indices with read_attachment, directory location, cache behavior, and non-extractable files. Comprehensive for a 2-parameter 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 the description adds significant context: explains refresh (ignore cache) and bidNtceNo (triggers download/extraction). Also details how results are used with other tools, adding value beyond schema 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 the tool downloads all attachments, extracts ZIPs (deleting originals), and returns a file catalog. It distinguishes from siblings: get_bid_attachments for URLs only, read_attachment for reading file 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?

Explicitly mentions when to use: when you need downloaded files and a catalog. Advises using get_bid_attachments for URLs only, and read_attachment with index for file content. Also explains refresh parameter for updated attachments.

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 set readOnlyHint=true and openWorldHint=true. Description confirms no file download ('파일 자체는 내려받지 않고 URL만 반환한다') and discloses API consumption details (up to 7 requests). No contradiction with annotations.

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?

Description is concise yet comprehensive. Main action stated first, followed by alternative tools and constraints, all in a logical flow. Every sentence serves a purpose 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?

Given the lack of output schema, the description adequately explains return values (file names and URLs from multiple sources). Also covers API request limits and scope. Complete for a single-parameter retrieval 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 description coverage is 100%, baseline 3. Description adds value by explaining the parameter's role and the return structure (results.notice·eorder·innovationRfp), going beyond schema to clarify output format.

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 it retrieves file names and download URLs for bid announcement attachments, specifying sources ('공고문·규격서·제안요청서·과업지시서 등', 'e발주·혁신장터RFP'). Distinguishes from sibling tools by listing what it does not do (download, read text, other details).

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 says when to use: '첨부의 URL만 필요할 때 쓴다' (when only URLs are needed). Provides clear alternatives: download_attachments for downloading files, read_attachment for reading text, and get_bid_basis_amount/get_bid_eligibility for other details.

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?

Adds context beyond annotations: explains that only three bid kinds exist for this tool and that unspecified bidKind results in 3 parallel API requests. Annotations already indicate read-only and open-world, so description complements them well.

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 sentences, front-loaded with the primary action, no redundant information. Every sentence contributes unique value, making it 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?

The description fully covers the tool's behavior for a simple two-parameter tool: explains the effect of bidKind on query count, clarifies data scope, and directs to sibling tools. No output schema exists, but the return values (amounts and rates) are implied.

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?

Adds significant meaning beyond the 100% schema coverage: clarifies that bidKind only covers three categories (no foreign/other), and explains the difference in API request count when specified vs. unspecified. This is valuable operational context not in 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?

Description clearly states it retrieves base amount, evaluation standard amount, and preliminary price range rate by bid notice number. It also distinguishes from siblings by naming get_bid_evaluation and get_bid_eligibility for other 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?

Explicitly says when to use ('when base values for budget estimation are needed') and provides alternative tools for related tasks (get_bid_evaluation, get_bid_eligibility). Also explains behavior for specified vs. unspecified bidKind.

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 indicate readOnlyHint=true and openWorldHint=true. The description adds behavioral context beyond annotations: change history exists only for three bid types, unspecified bidKind triggers 3 parallel API calls, and empty results indicate no changes. No contradictions.

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 long, front-loaded with the core purpose, and contains no redundant information. Every sentence adds value, efficiently covering purpose, usage context, and behavioral details.

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 no output schema, the description adequately explains the return values (corrected items, before/after values) and empty results. It covers the conditional behavior for bidKind specification and the API call implications. The description is complete given the tool's complexity and the rich annotations.

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%, baseline 3. The description adds value by explaining the parallel call behavior for bidKind and reiterating that the three enum values are the only supported types. It also clarifies the relationship between parameters and alternatives, which goes beyond schema 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 the tool retrieves change history for a bid notice by number, including corrected items and before/after values. It explicitly distinguishes from sibling tools like get_bid_basis_amount and get_bid_eligibility, making its purpose specific and unique.

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 this tool (to check how bid content changed after posting) and when not (for basis amount or eligibility, naming alternatives). It also explains the behavior for specified vs unspecified bidKind, including the trade-off in API call count.

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 and openWorldHint=true, indicating a safe read operation. The description adds context about the return focusing on license/region conditions per notice order but does not elaborate on specific output structure. With annotations covering safety, a moderate score is appropriate.

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 sentences with no redundancy. First sentence states purpose, second gives usage context, third explains parameter importance. 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?

Given the tool's simplicity (two parameters, read-only, no nested objects), the description covers purpose, usage, and parameter nuance. While it does not describe the return format, annotations (openWorldHint) imply variability. Overall, it provides sufficient context for correct selection and invocation.

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 both parameters. The description adds value beyond schema by explaining that bidNtceOrd is critical because license restrictions vary by order, that it should be sourced from get_bid_notice, and defaults to 000 if omitted. This provides operational guidance not present in 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 verb '조회한다' (queries) and the resource '면허제한·참가가능지역' (license restrictions and participation areas), and distinguishes itself from sibling tools by naming specific alternatives (get_bid_basis_amount, get_bid_change_history) for related but 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?

Explicitly says when to use: '투찰 가능 여부(면허·지역 조건)를 확인할 때 쓴다' (use when checking bid possibility for license/region conditions). Also provides explicit alternatives and explains the need for bidNtceOrd from get_bid_notice, including default behavior.

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 and openWorldHint, so the safety profile is clear. The description adds behavioral context: it performs a single query without work classification distinction and specifies the output structure (two keys: priceFormula, targetField), which goes beyond the annotations.

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 yet comprehensive: it front-loads the main action, provides usage context, lists alternatives, and explains the output structure in a single coherent paragraph without 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?

Given the tool has only one parameter, full schema coverage, no output schema but the description explains output keys, and provides sibling context, the description is complete enough for an agent to invoke 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?

Schema coverage is 100% (one parameter fully described). The tool description reinforces the parameter's purpose and adds context about the return value and alternative tools, enriching understanding 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 retrieves the bid evaluation formula (산식A) and evaluation main field (평가대상 주력분야) using the bid notice number. It distinguishes from siblings by listing alternative tools for related data.

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 explicitly states when to use this tool ('예정가격결정방법과 항목별 금액이 필요할 때') and provides named alternatives (get_bid_basis_amount, get_bid_eligibility, get_bid_change_history) for other needs.

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?

Description adds significant behavioral context beyond readOnlyHint and openWorldHint annotations: explains multiple API requests based on bidKind, default for bidNtceOrd, and absence of construction category. No contradictions with annotations.

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?

Description is concise (4 sentences) and well-structured: first sentence states purpose, second gives usage context, third mentions sibling tools, fourth provides behavioral details. 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?

Despite no output schema, the description adequately covers tool behavior: parameter roles, defaults, parallel request behavior, and relationship to other tools. All relevant aspects for correct invocation are addressed.

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%, but description enriches parameters with practical details: enum meanings (thng=물품, servc=용역, frgcpt=외자), request count implications, example for bidNtceNo, and dependency on get_bid_notice for bidNtceOrd.

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 the verb '조회한다' (query) and resource '구매대상물품' (bid items), specifies key parameters (입찰공고번호와 공고차수), and distinguishes from siblings by naming alternative tools for related 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?

Explicitly states when to use ('공고에 포함된 물품 내역이 필요할 때'), provides alternative tools for other needs (get_bid_basis_amount, get_bid_eligibility), and explains conditional behavior for bidKind (single vs parallel requests) and bidNtceOrd (default 000 if unspecified).

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 and openWorldHint. The description adds valuable behavioral details: multiple API calls if bidKind unspecified (up to 4 requests) and specific behavior for each bidKind value. No contradictions.

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?

Four efficient sentences, front-loaded with core purpose, no wasted 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 no output schema, the description adequately covers purpose, parameters, and behavior. Could mention response fields, but not necessary for this simple retrieval 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 has 100% coverage with descriptions. The description adds meaning: explains that unspecified bidKind triggers 4 queries, specified reduces consumption, and provides usage for 'etc'.

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 '입찰공고번호로 단건 공고의 상세를 조회한다' (retrieve details of a single notice by notice number) and contrasts with search_bid_notices, establishing a distinct purpose.

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 says when to use ('공고번호를 이미 알 때 쓴다') and when to use sibling ('조건으로 공고를 찾을 때는 search_bid_notices를 쓴다'). Also provides detailed guidance on bidKind parameter usage and API consumption.

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?

Discloses caching behavior (reuses downloaded files), auto-download if list missing, and non-extractable formats (body empty). Annotations give readOnlyHint=false and openWorldHint=true, and description aligns without contradiction, adding context beyond annotations.

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 paragraph of 4 sentences, front-loading the main purpose and covering key behaviors without waste.

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?

Covers formats, ZIP handling, streaming, and caching, but lacks explicit description of the return value structure (e.g., fields like text, truncated, savedPath). For a tool with no output schema, this is a minor 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 coverage is 100%, but description adds significant context: explains index usage from download_attachments response, offset/maxChars for streaming, and bidNtceNo to match the notice.

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 verb 'reads' the text body of a file, specifies the resource (files from download_attachments list), and distinguishes from siblings by naming download_attachments and get_bid_attachments.

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 tells when to use this tool vs alternatives ('목록을 먼저 받으려면 download_attachments를, 첨부 URL만 필요하면 get_bid_attachments를 쓴다.'), and explains how to handle long documents with offset/maxChars.

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 indicate readOnlyHint=true and openWorldHint=true (read-only, no side effects). The description adds important behavioral context: when bidKind is unspecified, it performs parallel searches for 4 types (excluding etc) consuming 4 API requests. This is beyond annotations and helps the agent understand resource usage.

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 mostly concise and front-loads the purpose. However, the second sentence ('조건에 맞는 공고 목록을 찾을 때 쓴다') is somewhat redundant with the first sentence. Minor improvement possible.

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 12 parameters, no required params, and no output schema, the description adequately covers the search criteria and distinguishes from siblings. It mentions the parallel search behavior but does not describe pagination or output format. Still fairly complete for its 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%, so baseline is 3. The description adds value by explaining the parallel search behavior for bidKind and traffic implications, which is not in the schema. This extra information merits a 4.

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 bid notices by various criteria (keyword, period, institution, region, industry, estimated price). It also distinguishes from sibling get_bid_notice by specifying that the sibling is for retrieving a single known bid notice.

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 states when to use this tool (when searching for bid notices by conditions) and when to use the alternative (get_bid_notice for known bid numbers). Also provides guidance on bidKind specification to save API traffic.

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