Skip to main content
Glama

lawmadi-os

by io.github.peter120525-cmd
OverviewDiscussionsAdmin

chat_leader

[KEY REQUIRED · 1 credit] 특정 리더와 1:1로 대화합니다. get_leaders에서 얻은 leader_id(예: 'L01', 'L32', 'CCO')를 넘기세요. 1회당 1크레딧이 차감됩니다(ask 와 같은 선예약 — 답변이 실패하면 환불). / Chat 1:1 with a specific legal leader. Provide the leader_id (e.g. 'L01', 'L32', 'CCO') from get_leaders. Each call costs 1 credit, reserved up front like ask and refunded if no answer is delivered. Pass history when continuing a conversation — otherwise the leader asks the same follow-up questions again.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesQuestion to ask the leader (max 2000 chars).
confirmNoDeprecated (2026-09-27): leader chat now costs 1 credit per call with no separate free allowance, so no confirmation step is needed. Accepted and ignored for backward compatibility.
historyNo이전 대화. 이것을 안 보내면 서버는 매 호출을 **첫 대화**로 보고 같은 것을 또 되묻습니다 — 리더가 물어본 뒤 답을 줄 때는 그 두 턴을 반드시 함께 넘기세요. 최근 20턴까지 반영됩니다. / Prior turns. Without this the server treats every call as a fresh conversation and asks the same questions again — when you answer a leader's follow-up, send those turns here. Up to 20 recent turns are used.
leader_idYesLeader identifier (e.g. 'L01'). See get_leaders.
client_tagNo선택. client_tag: 호출자 식별용, **응답에 영향 없음**(8~64자, 영숫자·_-.). 서버 로그에만 남아 호출을 골라 세는 데 씁니다. 형식이 어긋나면 무시합니다 — 거절하지 않습니다. 질의 본문에 섞지 마세요: 본문에 넣으면 질문의 일부가 되어 분류와 검증 결과가 달라집니다. / Optional caller label (8-64 chars). Logged only; never affects the response. Invalid values are ignored, not rejected. Do not put it in the query text — there it becomes part of the question.
idempotency_keyNo선택. 재시도 안전 키(8~64자, 영숫자·_-.). 30초 안에 안 끝나면 'pending'과 키를 돌려줍니다 — 같은 키로 다시 부르면 진행 중이거나 방금 끝난 답을 **새로 과금하지 않고** 받습니다. / Optional retry-safe key. If the chat takes longer than ~30s you get `pending` with a key; call again with the same key to collect the reply without a second charge.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "선택. 재시도 안전 키(8~64자, 영숫자·_-.). 30초 안에 안 끝나면 'pending'과 키를 돌려줍니다 — 같은 키로 다시 부르면 진행 중이거나 방금 끝난 답을 **새로 과금하지 않고** 받습니다. / Optional retry-safe key. If the chat takes longer than ~30s you get `pending` with a key; call again with the same key to collect the reply without a second charge.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / confirm / description
      Previous value: -"Spend credits when the free daily allowance is used up. Default false — nothing is ever charged without this. Only set it after a call returned status 'payment_required' telling you the cost."New value: +"Deprecated (2026-09-27): leader chat now costs 1 credit per call with no separate free allowance, so no confirmation step is needed. Accepted and ignored for backward compatibility."
  3. Changed1 schema field changed
    • addedInput schema / properties / client_tag
      Added value: +{
+  "description": "선택. client_tag: 호출자 식별용, **응답에 영향 없음**(8~64자, 영숫자·_-.). 서버 로그에만 남아 호출을 골라 세는 데 씁니다. 형식이 어긋나면 무시합니다 — 거절하지 않습니다. 질의 본문에 섞지 마세요: 본문에 넣으면 질문의 일부가 되어 분류와 검증 결과가 달라집니다. / Optional caller label (8-64 chars). Logged only; never affects the response. Invalid values are ignored, not rejected. Do not put it in the query text — there it becomes part of the question.",
+  "type": "string"
+}
  4. Changed1 schema field changed
    • addedInput schema / properties / history
      Added value: +{
+  "description": "이전 대화. 이것을 안 보내면 서버는 매 호출을 **첫 대화**로 보고 같은 것을 또 되묻습니다 — 리더가 물어본 뒤 답을 줄 때는 그 두 턴을 반드시 함께 넘기세요. 최근 20턴까지 반영됩니다. / Prior turns. Without this the server treats every call as a fresh conversation and asks the same questions again — when you answer a leader's follow-up, send those turns here. Up to 20 recent turns are used.",
+  "items": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "enum": [
+          "user",
+          "assistant"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "role",
+      "content"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
  5. Changed1 schema field changed
    • addedInput schema / properties / confirm
      Added value: +{
+  "description": "Spend credits when the free daily allowance is used up. Default false — nothing is ever charged without this. Only set it after a call returned status 'payment_required' telling you the cost.",
+  "type": "boolean"
+}
  6. Added

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does it well: it discloses a per-call credit charge, up-front reservation with refund on failure, the `pending` + idempotency_key path to avoid double charging, the 20-turn history window, and that client_tag is logged but never rejected or influential. These are real behavioral facts an agent cannot get from the schema alone.

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?

Front-loads the key facts (KEY REQUIRED, 1 credit, leader chat) before routing and cost detail, and every sentence carries information. The fully duplicated Korean/English text roughly doubles the length, which is defensible for an audience but not maximally tight.

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 6-parameter mutation-with-cost tool with no output schema and no annotations, the description covers the prerequisites (leader_id source), the cost/refund/pending semantics, conversation continuity via history, and the deprecated `confirm` flag. Nothing essential to invoking it correctly is missing.

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 100%, so the schema already documents every parameter, and the description largely restates it (leader_id examples, history purpose, deprecation of `confirm`). It adds the concrete 'CCO' example and reinforces that client_tag must not be embedded in the query, but the marginal value over the schema is limited.

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?

States a specific verb and resource — a 1:1 chat with a designated legal leader — and names get_leaders as the source of leader_id, so the agent knows exactly what this does. It does not explicitly contrast itself with the sibling tools `ask` / `ask_expert`, so the boundary between 'chat with a named leader' and generic Q&A is only implied.

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?

Gives clear operational context: fetch leader_id from get_leaders, and pass `history` when continuing so the leader does not repeat follow-up questions. It gives no explicit when-not-to-use guidance or direct comparison to `ask`/`ask_expert`, so an agent must infer when a leader chat beats a generic ask.

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

All lawmadi-os toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources