두 공법·개념의 차이를 대조한다 — 'RC 구조 vs 조적조 시공순서 차이', '스틱 vs 유닛 커튼월' 같은 비교/차이 요청에 호출하라(단일 순서는 scenario). 각각을 결정론 구성해 A/B 시퀀스, A에만/B에만 있는 단계, 공유 단계, contrasts 엣지를 반환한다. LLM 없음. a_coverage/b_coverage가 낮으면 그쪽 지식이 얇다는 정직한 신호 — 지어내지 말고 gaps 그대로 전하라.
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | 첫째 공법/개념 (예: RC 골조 시공). 'A vs B'를 a에 한 번에 줘도 됨. | |
| b | No | 둘째 공법/개념 (예: 철골 시공). a에 vs가 있으면 생략 가능. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses deterministic construction, 'LLM 없음', and honest coverage handling (a_coverage/b_coverage, gaps 전하라). It does not explicitly state side effects or permissions, but for a comparison tool these are less critical, and the disclosed behavior is substantive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence earns its place: purpose, usage routing, behavior, return structure, and honesty about gaps. It is front-loaded with the core purpose and examples before behavioral details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists and the tool has only two parameters, the description fully covers what an agent needs: what to invoke, when, how to handle coverage gaps, and how it differs from the sibling scenario. Nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 reinforces that 'a' can contain a combined 'A vs B' expression and that 'b' is optional, but these semantics are already present in the schema. It adds examples but no significant new parameter meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb (대조한다) and resource (두 공법·개념의 차이), provides concrete examples, and explicitly distinguishes itself from 'scenario' for single-order requests. An agent can immediately tell what compare does and when it applies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit when-to-use guidance ('비교/차이 요청에 호출하라') and names the alternative scenario ('단일 순서는 scenario'). This directly tells the agent how to route between siblings without further inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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.
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.
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.
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.