Skip to main content
Glama

den — Korean AEC knowledge, curated

feedback

사용자가 직접 입력하는 폼이 아니라, 호출 에이전트가 직전 Den 응답을 활용한 뒤 사용자가 보인 반응(수정 지시/불만/채택/무시)을 대화 종료 전 요약 수준으로 기록하는 릴레이 툴. query_id가 있으면 그대로 전달하고, 없으면 직전 Den 툴에 전달한 question_text만 전달한다. satisfied를 기록하고, 불만족이면 issue_type을 지정하며 comment는 반응 요지만 200자 이내로 요약한다. 채택·긍정은 satisfied=true, 수정 지시·불만·명시적 무시는 satisfied=false와 가장 가까운 issue_type으로 매핑한다. 관찰 가능한 반응이 전혀 없으면 만족 여부를 추측하지 않는다. ★satisfied=true(채택·긍정)이면 comment 에 den 이 없었으면 무엇을 하려 했는지 한 마디를 함께 적는다 — "다른 값을 쓰려 했다" · "몰라서 정하지 못하고 있었다" · "다른 출처로 갔어야 했다" 중 사용자가 실제로 말한 것. 이 한 마디만이 'den 을 썼다'와 'den 때문에 달라졌다'를 가른다. ★★사용자가 말하지 않았으면 비워 둔다. 추측해 지어내지 않는다 — 없는 것을 적는 편이 안 적는 것보다 나쁘다. ★★★그렇다고 comment 를 통째로 생략하지는 않는다. satisfied=true 면 무엇을 채택했는지 한 줄은 항상 적는다(어느 값·조문·판단을 그대로 썼는가). 비워 두는 것은 반사실 한 마디뿐이다 — 요지까지 비면 그 만족은 기록에 남아도 쓸 수 없다. 사용자 대화 원문은 전송하지 않는다. 만족/불만족과 사유는 다음 날 그래프 보완에 반영된다.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commentNoSummary of the user's reaction; never send conversation text. When satisfied=true this is expected, not optional: state in one line what the user actually did with the answer (which value / clause / decision they adopted). Also add what the user would have done without den (used a different value / was stuck undecided / would have gone to another source) — but ONLY if the user actually said it; never infer or invent that part. Omitting that one clause is correct when unsaid; omitting the whole comment is not.
query_idNoThe 16-character query_id returned in the previous response meta.
satisfiedYesWhether the previous Den response was satisfactory.
issue_typeNoRequired when dissatisfied: 오답, 무관, 기권과다, 얕음, or 기타.
question_textNoThe exact prior Den tool query, used only when query_id is unavailable.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.8/5.0
Behavior5/5

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

Despite having no annotations, the description extensively discloses behavioral rules: it does not send user conversation text, it requires a counterfactual comment only when actually stated, it forbids inventing content, and it explains that the feedback feeds into next-day graph improvement. It also clarifies the consequence of leaving comment empty for satisfied=true, showing deep transparency.

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 dense and rule-heavy, but each sentence earns its place and the most critical rules are highlighted with ★ markers for prominence. It is longer than ideal, but given the subtle behavioral requirements, the length is justified and the structure helps an agent parse the key dos and don'ts.

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 feedback-collection tool with no annotations and an output schema, the description covers all necessary details: what to record, how to map reactions, when to omit, what not to send, and what happens to the data. There is nothing an agent needs to know to invoke this correctly that is missing.

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 coverage is 100%, so the baseline is 3. The description adds meaningful semantic guidance beyond the schema: it explains the mapping of user reactions to satisfied/issue_type values, the exact mutual relation between query_id and question_text, and the nuanced rules for comment content (including the counterfactual clause and the prohibition on inventing). It also clarifies that issue_type should be set when dissatisfied and selected as the closest match. Because the description adds practical guidance on how and when to populate parameters, a 4 is justified.

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 identifies this as a relay tool for recording user reactions to a prior Den response, distinguishing it from form input and specifying exactly what it captures (satisfaction, issue type, comment summary) at conversation end. It uses specific verbs and resources, making the tool's purpose unmistakable and differentiating it from sibling tools which are all query/analysis 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 explicit conditions: use when there is a prior Den response, map positive reactions to satisfied=true and negative to false, do not guess if no observable reaction, and specify that query_id takes precedence with question_text as fallback. These are clear usage guidelines and exclusions.

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

A4/5.0
Disambiguation2/5

Several tools operate on the same underlying graph and can be confused: scenario and traverse both answer construction-order questions with overlapping examples, while answer_why, path_between, and evidence_for all deal with causal/conceptual connections. The descriptions are detailed and try to fence off compare, enumerate, and scenario, but the process/path cluster still has unclear boundaries.

Naming Consistency3/5

Tool names are readable and consistently lowercase snake_case, but the grammatical pattern varies widely: verb-only (compare, traverse), noun-only (scenario, feedback), verb_noun (review_plan), and compound noun/preposition forms (evidence_for, site_context, answer_why). It is mixed but not chaotic, so an agent can still infer each tool's role from its name.

Tool Count4/5

Twelve tools is a reasonable size for a broad curated AEC knowledge server and fits the ideal 3-15 range. The count is slightly inflated by overlapping process/path tools (scenario/traverse) and niche additions (emotional_palette, feedback), but it is not excessive.

Completeness4/5

The surface covers a wide range of reasoning types: causal explanation, comparison, classification, code retrieval, plan review, path traversal, sequence construction, site context, and evidence verification. The main gap is the lack of a direct generic 'what is X / define a concept' tool, which may require chaining multiple tools to get a simple definition.