Skip to main content
Glama

마케팅 보고 보관

marketing__report_archive__save

고객이 보관을 요청한 마케팅 성과 보고를 엑스보스에 보관하고 보관 번호(archived_report_id)를 돌려줍니다. report_content 에는 성과 보고 도구가 돌려준 결과를 그대로 넣고, 채널 이름과 보고 기간, 보고를 만든 시각(as_of)을 함께 넣습니다. 고객이 보관을 요청했을 때만 부르세요. 부를 때마다 한 건씩 새로 보관되니 같은 보고는 한 번만 보냅니다. 광고나 외부 기관에 아무것도 쓰지 않으며 로그인이나 연동이 필요 없습니다. 보관한 보고는 보관한 마케팅 보고 찾기 도구로 다시 찾습니다. For an authenticated call, generate and save request_idempotency_key before the first request. Reuse it with the same arguments only to recover that request after a lost response; use a new key for a new execution. Without it, calling again remains a new request. This optional key is not available to anonymous taste calls. Keep any provider-specific idempotency_key unchanged; it is a different field. 호출마다 토큰 1소진 요청 처리 시 XBOSS 작업을 생성하고 처리 결과를 저장합니다. 기관 원본의 조회 여부와 별개로 이 호출은 순수 읽기 전용이 아닙니다. 기관 데이터 변경은 도구별 실행 내용과 기존 확인 절차를 따릅니다.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "report_content": "<report_content>",
      "channels": "<channels>",
      "period_start": "<period_start>",
      "period_end_exclusive": "<period_end_exclusive>",
      "as_of": "<as_of>"
    },
    "name": "marketing__report_archive__save"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofYes보고를 만든 시각(결과의 as_of 값)
basisNo보고 주기(선택, 20자 이내). 예: 일, 주, 월
groundsNo보고의 근거 메모(선택)
channelsYes보고에 담긴 채널 이름 목록
period_startYes보고 기간 시작 날짜 (YYYY-MM-DD)
report_contentYes성과 보고 도구가 돌려준 결과 그대로
period_end_exclusiveYes보고 기간 끝 날짜(이 날은 빠진다) (YYYY-MM-DD)
retention_expires_atNo고객이 정한 보관 만료 날짜(선택, 없으면 만료 설정 없음) (YYYY-MM-DD)
request_idempotency_keyNoOptional same-request recovery key for authenticated calls; see the tool description.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description adds value by confirming each call creates a new stored record ('부를 때마다 한 건씩 새로 보관'), that it is '순수 읽기 전용이 아닙니다', that it writes nothing to ad platforms or external agencies, and that each call consumes one token. It also explains the safe-retry protocol for request_idempotency_key (new key per execution, reuse only to recover a lost response), which goes well 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The Korean opening through '보관한 마케팅 보고 찾기 도구로 다시 찾습니다' is front-loaded and efficient. However, a long English idempotency paragraph and trailing boilerplate about token consumption, XBOSS job creation, and '기관 데이터 변경' (institution data changes, irrelevant to a marketing archive) are verbose, mixed-language, and partly generic.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter mutation tool with no output schema, the description supplies the return value, the provenance requirement for the nested report_content object, the duplicate-call hazard, the side-effect boundary, and the retrieval path. Nothing essential to invoking it correctly appears to be missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds genuine semantics: report_content must be the report tool's output verbatim, accompanied by channel names, period, and as_of. It is also the authoritative explanation for request_idempotency_key, which the schema only defers to the description for, and it warns not to conflate it with a provider-specific idempotency_key.

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

Purpose5/5

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

The opening sentence states a specific verb and resource (archive a customer-requested marketing performance report into XBOSS) and names the return value (archived_report_id), which lets an agent distinguish it from sibling marketing__report_archive__list at a glance. The closing sentence reinforces the split by pointing back to the retrieval tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Guidance is explicit: '고객이 보관을 요청했을 때만 부르세요' states the trigger, and '같은 보고는 한 번만 보냅니다' warns against duplicate calls. It also names the retrieval sibling for the opposite operation, though it does not name the report-generating tool whose output feeds report_content, only describing it generically as '성과 보고 도구'.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources