Skip to main content
Glama

마케팅 성과 보고

marketing__growth_review__compute

채널별 광고비와 고객이 입력한 매출, 신규 유료 고객 수로 마케팅 성과 보고를 계산합니다. channels 에는 채널 이름과 그 기간의 광고비를 넣습니다. 계산하는 지표는 ROAS(광고비 대비 매출)와 CAC(신규 유료 고객 1명당 광고비) 두 가지이고, goal 에 목표를 넣으면 목표 대비 실적을 함께 돌려줍니다. 매출이나 고객 수가 없거나 통화가 섞이면 그 지표는 값 대신 사유를 돌려주며 숫자를 지어내지 않습니다. 입력한 숫자로 계산만 합니다. 외부 기관이나 광고 계정을 부르지 않으며 로그인이나 연동이 필요 없습니다. 로그인한 호출이면 첫 요청 전에 request_idempotency_key 값을 만들어 저장하세요. 응답을 받지 못한 그 요청을 되찾을 때만 같은 인자와 함께 그 값을 다시 보내고, 새로 실행할 때는 새 값을 쓰세요. 이 값 없이 다시 부르면 새 요청이 됩니다. 계정 없이 맛보기로 부를 때는 이 선택 칸을 쓸 수 없습니다. 기관 업무에 따로 있는 idempotency_key 칸은 다른 칸이니 그대로 두세요. 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_period": "<report_period>",
      "channels": "<channels>"
    },
    "name": "marketing__growth_review__compute"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNo목표값. 넣은 항목만 목표 대비 실적을 돌려준다
channelsYes채널별 광고비 목록. 빈 목록도 받는다
leads_actualNo보고 기간의 실제 리드 수(목표 대비 실적)
report_periodYes보고 기간. 끝 날짜는 포함하지 않는다
customer_revenueNo고객이 직접 넣는 매출. 기간과 통화가 보고와 다르면 매출 지표는 값 대신 사유를 돌려준다
new_paid_customersNo보고 기간의 신규 유료 고객 수(CAC 분모, 목표 대비 실적)
request_idempotency_keyNo로그인한 호출에서 응답을 못 받은 같은 요청을 되찾을 때 쓰는 선택 값입니다. 쓰는 법은 도구 설명에 있습니다.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / request_idempotency_key / description
      Previous value: -"Optional same-request recovery key for authenticated calls; see the tool description."New value: +"로그인한 호출에서 응답을 못 받은 같은 요청을 되찾을 때 쓰는 선택 값입니다. 쓰는 법은 도구 설명에 있습니다."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

The annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=true; the description goes well beyond them by disclosing that each call consumes one token, that request processing creates an XBOSS task and stores its result, and that the call is explicitly not pure read-only. It also commits to a no-fabrication error contract (missing or mixed-currency data returns a reason rather than a value) and spells out idempotency recovery semantics. The claim that it calls no external institutions is in mild tension with openWorldHint=true, but the task-creation disclosure makes the non-read-only annotation consistent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

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

The definition is front-loaded: purpose and metrics first, then error/degradation behavior, then idempotency and cost semantics. Most sentences carry operational weight, though there is scaffolding noise unrelated to this tool's job, such as the trailing line about institution data changes following per-tool confirmation procedures, and one run-together sentence about token consumption and XBOSS task creation that hurts readability.

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

Completeness4/5

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

For a 7-parameter tool with nested objects, no output schema, and full schema coverage, the description covers the remaining burden: what is computed, how degraded results are signaled, side effects and per-call cost, and complete idempotency protocol. The main residual gap is that no shape of the returned report is sketched beyond the two named metrics and goal comparison, which an agent must discover at call time.

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 would be 3, but the description adds genuine meaning: it defines what channels entries represent, that goal yields target-vs-actual only for supplied fields, and that period or currency mismatch on customer_revenue degrades the revenue metric to a stated reason. Critically, the schema entry for request_idempotency_key explicitly defers ('쓰는 법은 도구 설명에 있습니다') to the description, which then supplies the full create-once/resend-same-value/guest-cannot-use rules and distinguishes it from the institution's separate idempotency_key field.

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

Purpose4/5

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

The description opens with a specific verb and resource: it computes a marketing performance report from channel ad spend, customer-supplied revenue, and new paid customer counts, and names the two metrics produced (ROAS and CAC). It also implicitly separates itself from ad-account-pulling siblings by stating it calls no external ad accounts, but it never names an actual sibling tool, so routing still requires inference.

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

Usage Guidelines3/5

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

Usage context is present but indirect: it explains that supplying goal enables target-vs-actual output, that missing revenue/customer counts yields a reason instead of a number, and that no login or integration is required. What is absent is explicit routing against near neighbors such as marketing__lead_to_revenue__reconcile, marketing__optimization__suggest, or marketing__report_archive__save, and there is no statement of when this tool is the wrong choice.

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