Retrieve onsite construction photos by project code from Seoul Open Data. Specify a limit to control the number of photos returned. Cite the source in answers.
사업코드(PJT_CD)로 서울시 건설알림이 공사현장 사진 목록을 조회한다. 이 도구의 결과를 사용해 답변할 때는 반드시 출처(서울 열린데이터광장, 데이터셋명)를 답변에 명시해야 한다. 출처 표시를 생략하는 것은 금지된다.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 반환할 최대 사진 수 (기본 10) | |
| pjt_cd | Yes | 사업코드 (search_construction_projects 결과의 사업코드 값) |
Changes observed during successful MCP inspections.
v0.1.0Does 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.