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

With no annotations, the description carries the behavioral disclosure burden and does well: it discloses that gu_name and min_amount are filtered client-side after retrieval, that 0 progress values should be displayed as '미입력', and that source attribution is mandatory when citing results. It could mention pagination or rate limits, but the disclosed behaviors are meaningful and non-obvious.

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 compact paragraph that front-loads the core purpose, then adds filtering behavior, display conventions, and citation requirements. Every sentence adds relevant operational context, though a minor typo ('담당자' appears as '담당자') and slight redundancy with schema descriptions prevent a perfect score.

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 annotations and no output schema, the description covers the key operational needs: what is returned, how filtering works, how to handle zero values, and the mandatory source citation. It could be more complete about result ordering, API metadata, or error behavior, but the core information needed to invoke and interpret results is present.

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 provides 100% parameter descriptions, including the client-side filtering notes for gu_name and min_amount. The tool description adds little parameter-level meaning beyond restating that search is keyword-based and that filtering happens client-side. Baseline 3 is appropriate because 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 clearly states it searches Seoul construction progress data by business name and ordering agency keyword, and enumerates the specific fields returned (progress rates, amounts, responsible parties, location). It does not explicitly distinguish itself from sibling tools like search_construction_projects, but the emphasis on progress-specific fields makes the purpose reasonably clear.

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 gives useful context about client-side filtering for gu_name and min_amount, but it provides no guidance on when to use this tool versus the sibling tools such as search_construction_projects or search_construction_work_by_district. There are no explicit exclusions or alternative-selection criteria.

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 the full burden of behavioral disclosure. It does reveal that the operation is a read-only lookup ('조회한다') and imposes a mandatory source-citation rule for answers using its output, which adds behavioral context. However, it omits details about pagination, photo URL formats, ordering, or possible variations in results, so transparency is only partial.

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 tightly structured: two sentences, the core action first, and the important usage caveat (source attribution) following immediately. Every sentence earns its place with no redundant or vague wording.

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 simple two-parameter lookup with one required input, the description covers the operation and a behavioral requirement, and the schema covers parameter details. The absence of an output schema means the description does not mention what fields the photo list contains (e.g., URLs, dates, metadata), but the tool's purpose is simple enough that 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%: both limit and pjt_cd have type, constraints, and descriptions. The pjt_cd parameter description adds meaning beyond the name by pointing to search_construction_projects results as the source of valid values, which helps the agent construct a correct call.

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 specific action ('조회한다' – retrieves) and a specific resource ('공사현장 사진 목록' – construction site photo list) keyed by business code. This clearly distinguishes it from sibling tools that search projects, work by district, or get progress, none of which target photos.

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 makes the input need explicit: a business code (PJT_CD) is required, and the pjt_cd parameter description further specifies that the value comes from search_construction_projects results, establishing a clear follow-up workflow. It does not explicitly mention when not to use the tool or compare with siblings, but the context is clear enough for an agent to select it appropriately.

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 behavioral disclosure burden. It adds useful behavioral context by requiring mandatory source attribution when results are used, and it lists the key data fields returned. It does not mention rate limits, data freshness, or result pagination, but as a read/search tool this is a moderate rather than critical 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?

The description is front-loaded with the main function, followed by the return-value summary and then the important attribution rule. It is three sentences with no filler; though the return-field list is somewhat long, every sentence contributes meaningful 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 is no output schema and no annotations, yet the description covers search criteria, returned fields, and a mandatory source-citation requirement. However, it leaves unclear how it differs from the sibling search_construction_work_by_district, and it does not describe result order, pagination, or edge cases, so it is not fully 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?

Schema description coverage is 100%, so the schema already fully documents the three parameters. The description repeats the gu_name/keyword search idea but does not add meaning beyond the schema's parameter descriptions, so the baseline score of 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 states a specific action ('검색한다') on a specific resource (서울시 건설알림이/One-PMIS 공사장 목록), with clear filter criteria and a detailed list of returned fields. It does not explicitly differentiate itself from the sibling tool search_construction_work_by_district, which is similarly named, but its overall purpose is unambiguous.

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 it: when searching construction project lists by 자치구명 or keyword. However, it provides no explicit guidance about when NOT to use it, and it does not compare itself with the similarly named sibling search_construction_work_by_district, leaving a potential routing ambiguity.

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 explicitly states that when gu_name is provided, the API server filters by that district, lists the returned fields, and imposes a mandatory source-citation rule for answers. This goes beyond a bare search description, though it omits details like pagination, errors, or data freshness.

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 front-loaded: it names the source and action first, then explains filtering behavior, return fields, and the citation requirement. Every sentence earns its place and there is 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 a tool with no output schema and no annotations, the description covers invocation and answer-citation behavior reasonably well. However, it lacks guidance for choosing between this and search_construction_projects, and it leaves open whether at least one of gu_name or biz_name must be supplied, which matters for correct usage.

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 the schema already documents gu_name, biz_name, and limit. The description mostly restates the schema's server-side filtering behavior and keyword semantics rather than adding new meaning. It does not clarify whether the two search parameters are mutually exclusive or combinable.

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 specific action (search), the resource (ListConstructionWorkService), the search keys (gu_name, biz_name), and the returned fields. However, it does not explicitly distinguish itself from sibling tool search_construction_projects, and allowing project-name keyword search creates overlap risk.

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 needing Seoul construction work information filtered by district or project keyword. It gives no explicit guidance about when not to use it, whether to prefer search_construction_projects, or whether gu_name and biz_name can be combined.

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