Skip to main content
Glama

고객 확인 후 검토 요청 제출

handam_public_submit_for_review
Idempotent

고객이 확인 요약(정확한 revision·confirmationFingerprint)에 동의한 뒤에만 호출합니다. 초안이 "운영자 검토 대기(requested)"가 되며 운영자가 사람으로서 확정합니다. 확정·결제·배차·발주가 아니며, 요약 이후 초안이 바뀌었으면 거부됩니다. 같은 requestId 재시도는 같은 결과를 돌려줍니다.

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": {
      "orderId": "<orderId>",
      "requestId": "<requestId>",
      "revision": "<revision>",
      "confirmationFingerprint": "<confirmationFingerprint>",
      "acknowledged": "<acknowledged>",
      "profileId": "<profileId>",
      "ownerCapability": "<ownerCapability>"
    },
    "name": "handam_public_submit_for_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
orderIdYes
revisionYes
profileIdYes첫 접수 응답의 profile.profileId (조회 키일 뿐 권한이 아님)
requestIdYes
acknowledgedYes
ownerCapabilityYes첫 접수 응답에 한 번만 제공된 소유자 확인값. 클라이언트가 안전하게 보관해야 하며 다른 사용자와 공유하면 안 됩니다.
confirmationFingerprintYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / acknowledged / type
      Added value: +"boolean"
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), the description discloses the state transition, that a human operator performs final confirmation, that a stale draft since the summary causes rejection, and that retrying with the same requestId returns the same result. These are exactly the mutation-safety facts an agent needs.

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

Conciseness5/5

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

Five short sentences, with the call precondition front-loaded and each subsequent sentence carrying a distinct fact (state outcome, non-goals, rejection rule, idempotency). Nothing repeats the annotations or the schema.

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 state-transition mutation with no output schema, the description covers preconditions, resulting state, rejection behavior, and idempotency. It does not indicate what the response returns or any auth/permission expectations beyond the schema-level ownerCapability note.

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 description coverage is low (29%), so the description must compensate, and it does for the key fields: revision/fingerprint must match the summarized draft or the call is rejected, and requestId drives the idempotent retry result. It says nothing about acknowledged or orderId, leaving some of the seven required parameters to the schema alone.

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 description states a specific verb and resource (submit the draft for review) and the resulting state ("운영자 검토 대기(requested)"), then explicitly rules out adjacent actions (확정·결제·배차·발주). An agent can tell this apart from a confirm/commit call without opening the schema.

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?

It gives a hard precondition — call only after the customer agrees to the confirmation summary with the exact revision and confirmationFingerprint — which implies the preview step before calling. It does not name the preview sibling explicitly, so the routing is inferred rather than stated.

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