lookup_dictionary원불교 대사전 4,523항목. q로 표제어·한자·정의문을 찾는다(표제어가 정확히 하나 걸리면 곧바로 본문). id를 주면 그 항목. get_passage의 각주에 붙은 [대사전 ****]가 그 id다. 긴 항목(일원상·사은·법위등급 등)은 첫 절만 내주고 나머지 절 목록을 알려 준다 — 필요한 절을 section으로 다시 부른다.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | 찾을 말(표제어·한자·정의문) | |
| id | No | 대사전 항목 id — 주면 q는 무시하고 그 항목을 낸다 | |
| limit | No | 돌려줄 최대 건수(기본 10) | |
| section | No | 긴 항목에서 읽을 절 이름(부분 일치). 앞선 호출이 알려 준 절 목록에서 고른다 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the read-only annotations, it disclosures a nontrivial truncation behavior: long entries return only the first section plus a section list, requiring a follow-up call with section. It also discloses the exact-one-hit shortcut and the id-overrides-q behavior, which are practical execution details an agent needs.
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?
Three dense sentences with no filler: resource identity, q/id semantics, and long-entry handling are each covered in one focused sentence. The most important usage modes are front-loaded, and every sentence earns its place.
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?
For a read-only lookup tool with all parameters documented and no output schema, this description covers the key operational edge cases: single-hit vs multi-hit behavior, direct id lookup, and the truncation/section workflow. Nothing essential for correct invocation 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 adds value by explaining the source of id (get_passage footnote markers), the exact-match behavior for q, and the two-step section workflow for long entries. This exceeds what the parameter descriptions alone provide.
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?
States a specific verb and resource: '원불교 대사전 4,523항목. q로 ... 찾는다' and 'id를 주면 그 항목'. It clearly identifies the tool as a dictionary lookup with multiple access modes, and the dictionary scope separates it from siblings like search_scripture or search_sungga.
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?
Gives clear invocation contexts: q for headword/hanja/definition search, id for direct lookup, and section for re-reading truncated long entries. The cross-reference to get_passage's [대사전 ****] footnote is a concrete routing cue. It doesn't explicitly list when-not-to-use alternatives, hence not a full 5.
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.
Each tool maps to a distinct operation: structural navigation, passage reading, related-passage discovery, book listing, dictionary lookup, scripture search, and hymn search. There is no meaningful overlap, and tools such as search_scripture and lookup_dictionary are clearly differentiated by corpus and lookup behavior.
All tool names follow the same snake_case verb_noun pattern: get_outline, get_passage, get_related, list_books, lookup_dictionary, search_scripture, search_sungga. The verbs are uniform in style and the object of each action is immediately clear.
Seven tools is well-scoped for a scripture research server, covering navigation, reading, searching, dictionary lookup, cross-referencing, and hymn lookup. Each tool earns its place and none feels redundant or unnecessary.
The tool surface covers the full research workflow: discovering books, navigating outlines, reading and citing passages, full-text searching, dictionary lookup, related-passage discovery, and hymn search. Search results return ids that feed into get_passage, and dictionary footnotes are linked via ids, so there are no obvious dead ends.