Skip to main content
Glama

복대리 · Bokdaeri

복대리 상담 확인 계속

continue_consultation_request

Continue a specific reviewed preview after user confirmation or hand it off for web confirmation.

지정한 미리보기에 대한 이용자의 동의를 기록하거나(confirm_and_continue), 복대리 웹에서 직접 확인하도록 연결합니다(handoff). 현재 진행 ID·버전과 미리보기 ID가 필요하며, 이 단계만으로 접수되지는 않습니다.

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": {
      "journey_id": "<journey_id>",
      "expected_journey_revision": "<expected_journey_revision>",
      "review_id": "<review_id>",
      "mode": "<mode>"
    },
    "name": "continue_consultation_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
phoneNo사용자가 이번 대화에서 직접 말한 연락받을 휴대전화번호(선택). 복대리 인증 화면에 미리 채우기만 하고 발송·인증은 화면에서 본인이 합니다. 인증번호는 절대 받지 않습니다.
review_idYes
journey_idYes
expected_journey_revisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only tell the agent this is a non-read-only, non-destructive, non-idempotent, closed-world call. The description adds the substantive behavior beyond that: consent is *recorded* rather than the request being submitted, an alternative handoff path exists, and the call is keyed to the *current* journey revision, implying optimistic-concurrency rejection if it is stale. It stops short of saying what state is persisted or what the caller receives, which keeps it out of 5 territory.

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?

Two tight sentences, front-loaded with the core action and then the mode split, with zero filler. The mixed English/Korean phrasing is slightly harder to scan but no sentence is redundant.

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

Completeness3/5

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

For a 5-parameter non-idempotent state-changing call with no output schema and thin annotation detail, the description covers prerequisites and the no-submission guarantee but never says what happens after a successful call (a next-step token, a handoff URL, a pending status) or how failures surface. The agent can select the tool and pick a mode, but cannot anticipate the result.

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

Parameters3/5

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

Schema description coverage is only 20% (only phone is documented in-schema), so the description has to carry weight: it explains both enum values of mode with real semantics and stresses that journey ID/version must be current, adding meaning for expected_journey_revision. It does not explain the relationship or expected values of journey_id vs review_id beyond the word '미리보기 ID', leaving half the required parameters to pattern-only schemas.

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 states a specific verb and resource ('Continue a specific reviewed preview') and immediately splits it into the two concrete outcomes it can produce: recording consent (confirm_and_continue) or handing off to the web (handoff). It also explicitly bounds the operation with '이 단계만으로는 접수되지는 않습니다', which distinguishes it from submit_consultation_request without naming it. A sibling name would have made it a 5.

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?

The two modes are described with the condition that selects each: use confirm_and_continue to record the user's consent for the specified preview, use handoff when the user should confirm on the 복대리 web. It also states the prerequisite state (current journey ID/version and preview ID) and the exclusion that this alone does not submit. It does not say what to run first (e.g., a prepare/preview tool) or what to do if the revision is stale, so the routing is clear but not exhaustive.

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