Skip to main content
Glama
Sign In
jade-mcp

jade-mcp

by choiyounggi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

근태/근무 취소 신청 상신

jade_commit_attendance_cancel
Destructive

Submits an attendance or work cancellation request to the approval line using a prepared token, rechecking cancellability and preview match; call only after explicit user approval.

Instructions

jade_prepare_attendance_cancel 이 준 토큰으로 근태/근무 취소 신청서를 결재선에 상신한다. 상신 직전에 화면을 새로 열어 그 원신청이 아직 취소 가능한지 다시 확인하고 미리보기와 같을 때만 보낸다. 결재자에게 바로 전달되므로 사용자가 미리보기를 보고 명시적으로 승인했을 때만 호출한다.

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": {
      "token": "<token>"
    },
    "name": "jade_commit_attendance_cancel"
  }
}

Input Schema

NameRequiredDescriptionDefault
tokenYesjade_prepare_attendance_cancel 이 돌려준 토큰

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, non-idempotent, and openWorld, so safety basics are covered. The description adds genuinely new behavior: it re-opens the screen right before submitting, re-verifies the original request is still cancellable, and aborts unless the state matches the preview. It does not spell out what happens after submission (whether the request can be withdrawn), which leaves a small gap for a destructive irreversible action.

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?

Three short sentences, front-loaded with the core action and prerequisite, followed by the safety verification and the approval precondition. No redundant or filler wording.

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 single-token destructive commit tool with no output schema and rich annotations, the description covers the prerequisite, the pre-submit verification, and the human-approval gate — everything an agent needs to decide to call it.

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?

Only one parameter, and schema coverage is 100% with the schema description already saying the token comes from jade_prepare_attendance_cancel. The description restates the same provenance and adds no further semantics (e.g., token lifetime or reuse), so this is the baseline case.

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?

States a specific verb (상신/submit to approval line) and resource (근태/근무 취소 신청서), and names the sibling that produces its input (jade_prepare_attendance_cancel). It is clearly distinguishable from the prepare step and from other commit_* siblings by the resource it submits.

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

Usage Guidelines5/5

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

Explicitly scopes invocation to the case where the user has seen the preview and given explicit approval, and implicitly rules out calling it without a prepare-issued token. The when-to-call condition is stated rather than left to inference.

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

Deploy Server

Other Tools