Skip to main content
Glama

답변 오류 신고

report_issue

답이 틀렸을 때 신고하거나(kind='결함'), 남길 값이 있는 질문 원문을 기록한다(kind='질문기록').

**결함**: 사용자가 "틀렸다"·"이상하다"고 하면 **먼저 이 도구를 부른 뒤** 정정 답변을 하라.
추측으로 부르지는 말 것.

**질문기록**: 이 서버는 클라이언트가 이미 도구 호출로 번역한 뒤를 보므로 **사용자의 원문
질문을 볼 수 없다**. 그래서 어떤 질문이 실제로 오는지, 무엇을 못 답하는지가 계측에 안 잡힌다
— 이 프로젝트의 목적이 유통이 아니라 계측인데 정작 수요 축이 비어 있었다. 복합 질문·부분
답변·전제 오류 셋 중 하나면 원문(일반형으로 치환)을 남겨라. **개인 식별 조합은 반드시
일반형으로 바꿔서** 넣는다.

두 종류가 한 도구인 이유: 무인증 공개 서버라 쓰기 표면을 하나로 묶어 상한을 함께 건다
(CLAUDE.md 규칙 2). 시간당 상한도 공유한다.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNo'결함'=답이 틀렸다는 신고(기본). '질문기록'=틀리진 않았지만 **질문 원문을 남길 값이 있는 경우** — 서버는 클라이언트가 번역한 도구 호출만 보고 원문 질문을 볼 수 없어서, 이게 유일한 통로다. **아무 질문이나 남기지 마라**: ①여러 도구를 엮어야 답이 된 복합 질문 ②우리 도구로 일부만 답한 질문(answered_fully=false) ③사용자의 전제가 틀려서 바로잡아야 했던 질문(예: '펜션'을 법적 업종명으로 알고 있던 경우) — 셋 중 하나일 때만. 단순 조회 한 건은 남기지 않는다결함
problemNo무엇이 틀렸는지. 사용자의 말을 그대로 옮겨도 된다. kind='결함'이면 필수, kind='질문기록'이면 비워도 된다.
expectedNo사용자가 맞다고 본 값
questionNo사용자의 **원래 질문**(kind='질문기록'이면 필수). ⚠️ **개인 식별 조합은 일반형으로 치환해서 넣어라** — 이름·연락처·정확한 거주지·동행자 사연이 겹치면 그대로 적지 말 것(예: '○○동 △△빌라 사는 김□□, 부모님 팔순으로 속초 2박' → '가족 3인 속초 2박'). 무인증 공개 서버의 로그다
tool_usedNo문제가 된 답을 만든 도구
wrong_valueNo틀린 수치·문장
missing_axisNoanswered_fully=false일 때 **없어서 못 답한 축**(예: '실시간 빈방', '가격대 필터 없음', '반려동물 동반 가능 여부 미수록'). 로드맵과 수집 우선순위의 원천이 된다
answered_fullyNokind='질문기록' 전용 — 이 서버 도구만으로 질문에 **완결된 답**을 했는가. false면 missing_axis에 무엇이 없었는지 적어라

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.6/5.0
Behavior5/5

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

Even though annotations show mutability flags, the description adds meaningful behavioral context: it writes to an unauthenticated public server, shares an hourly cap, cannot see the client's original question, and requires PII anonymization. No contradiction with annotations exists.

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 description is well-structured with bold headers and clear sections for the two modes. It is fairly long, but the complexity of a dual-purpose tool justifies the length; a short project-context aside could be trimmed but does not significantly hurt clarity.

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 tool with 8 parameters and no required fields, the description supplies all missing decision logic: when to report defects, when to log questions, PII handling, shared rate limits, and how missing_axis feeds the roadmap. The output schema already covers return values, so no further detail is needed here.

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?

The input schema already covers all 8 parameters with rich descriptions (100% coverage), so the baseline is 3. The description reinforces decision heuristics around kind and missing_axis but does not add parameter-level syntax or format details beyond the schema.

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 clearly names two specific actions—신고 (report defects) and 기록 (log original questions)—with the kind parameter distinguishing them. It is unmistakably different from the sibling stay_* tools, which are lookup/booking tools.

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?

The description gives an explicit ordering rule: call this tool before issuing a correction, and warns against speculative calls ('추측으로 부르지는 말 것'). It also defines the three eligible conditions for question logging (complex, partial, false premise) and explains why both modes share one tool (rate limiting).

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.

TDQS

A4.1/5.0
Disambiguation4/5

Tools are largely distinct: search finds stays, detail shows one, booking_link generates a referral URL, and report_issue handles feedback. The single ambiguity is report_issue combining two kinds (defect and question logging), but its descriptions clarify the usage.

Naming Consistency3/5

Three tools follow a stay_ prefix pattern (stay_search, stay_detail, stay_booking_link), but report_issue breaks the convention and uses a separate prefix. The structure is mixed (verb, noun, compound) though still readable.

Tool Count5/5

Four tools is well-scoped for a referral service: search, detail, link generation, and issue reporting. Each tool has a clear role with no redundancy or missing essentials.

Completeness4/5

The surface covers the core journey (find, view, link out) and adds issue tracking. It lacks direct booking or availability filtering, but that is intentionally delegated to external platforms, so the coverage is reasonable for the stated purpose.

Resources