Skip to main content
Glama

MyKIFRS

기준서 문단 원문

get_paragraph
Read-onlyIdempotent

MyKIFRS MCP의 get_paragraph 도구는 기준서 문단 전문을 앞뒤 문맥과 함께 반환합니다.

[Purpose]

  • To quote a found 문단 exactly — the search snippet is never quotable evidence.

  • To check 조건절·예외 with neighbors — a lone 문단 invites misreading.

[Usage]

  1. "1116호 33문단 원문" → unique_key="1116-33"

  2. "앞뒤로 더 넓게 보여줘" → unique_key="1116-33", context=5

  3. "이 문단만 딱" → unique_key="1115-B58", context=0

[Response]

  • { standard:{std_num, title, category}, target, related_qnas:[doc_number], items:[…] }

  • items[]: { seq, item_type, unique_key, para_num, level, title, ref, content_text }

  • item_type: "paragraph" = 본문, "title" = 제목 행.

  • related_qnas: doc_number array (e.g. ["GKQA01-085"]) — feed each to get_qna.

  • Unknown key returns { error: "문단 없음: {unique_key}" }.

[Rules]

  • unique_key = "{기준서번호}-{문단번호}". 문단 numbers aren't digits-only (B58·AG12·SP1.2·6.1.1) — pass the value verbatim, never normalize it.

  • context expands within the same 기준서 part only — boundaries return fewer items; not an error.

  • Quote content_text, never a search snippet.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contextNo앞뒤로 포함할 항목 수 (기본 2)
unique_keyYes문단 키 (예: '1116-33')

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral detail beyond annotations: response shape, item_type semantics, unknown-key error format, context boundary behavior within the same standard part, and the instruction to quote content_text rather than snippets.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured into Purpose, Usage, Response, and Rules sections, each earning its place. The most critical guidance — exact quoting and the unique_key format warning — is front-loaded, and there is no filler or repetition.

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?

With no output schema, the description fully documents the return structure including items fields, item_type values, related_qnas handling, and error responses. It also covers edge behavior such as context boundaries producing fewer items and non-numeric paragraph keys, making the tool safely callable without additional assumptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are documented in the schema, but the description adds essential semantics: unique_key values are not always digits-only (B58, AG12, SP1.2) and must be passed verbatim, and context expands only within the same standards part. The examples directly tie the parameters to real user intent.

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 states a specific verb and resource: returns the full original text of an accounting standard paragraph with surrounding context. It clearly differentiates from search tools by stating that search snippets are never quotable evidence, which positions get_paragraph as the tool for exact quotation.

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?

The description gives concrete usage examples ('1116호 33문단 원문', '앞뒤로 더 넓게 보여줘') and explains when to use context=0 versus context=5. It implies the alternative is any search tool's snippet output, but it does not explicitly name sibling tools like search_standards or search_qnas as the tools to use before get_paragraph.

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

A4.8/5.0
Disambiguation5/5

The verb prefixes (get/search/list) plus distinct nouns (paragraph, qna, standards, usage_stats) make each tool's purpose unmistakable. search_standards and search_qnas target different corpora, and get_paragraph/get_qna retrieve by unique key versus full-text search, so no two tools overlap.

Naming Consistency5/5

Every tool follows the verb_noun snake_case pattern: get/retrieves by key, search/does full-text queries, list/returns the catalog. The naming perfectly mirrors the tool behavior, making the set predictable and easy to navigate.

Tool Count5/5

Six tools is well-scoped for a standards/Q&A reference server: catalog (list_standards), full-text search over two corpora (search_standards, search_qnas), keyed retrieval for each (get_paragraph, get_qna), and one telemetry tool. Each tool earns its place with no redundancy.

Completeness4/5

The core retrieval workflow is complete: list catalog → search corpus → fetch full text, and search Q&A → fetch Q&A response, with get_paragraph even linking to related Q&As. Minor gaps exist such as no way to browse a standard's full paragraph structure or enumerate Q&A documents without a search query, but agents can work around these.

Resources