Skip to main content
Glama

ingest_raw

Convert raw source documents into LLM-generated wiki notes on demand by processing a specific file or a limited batch from the raw directory.

Instructions

raw 디렉토리의 원문을 LLM으로 위키 노트로 변환 (수동 트리거).

watch 데몬의 자동 변환과 동일한 경로를 사용하되, 필요할 때 즉시 실행한다. Open WebUI 등 OpenAI 호환 엔드포인트 설정(WIKI_INGEST_*)이 필요하다.

Args: file: 특정 파일명만 처리 (raw 디렉토리 기준). 빈 값 시 디렉토리 전체. limit: 전체 처리 시 최대 개수 (기본 10).

Returns: JSON — 처리 결과 목록 (파일별 status/id/error).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ingest_raw"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
limitNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose a real prerequisite: OpenAI-compatible endpoint settings (WIKI_INGEST_*) must be configured, plus that it invokes an LLM. It does not say whether existing notes are overwritten, what happens on partial failure, or that LLM calls carry cost/latency, which leaves meaningful gaps for a write-producing tool.

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 core action is front-loaded in the first sentence, followed by execution context, prerequisites, then Args/Returns. No sentence is filler, though the explicit Returns block is partly redundant given an output schema exists.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Config prerequisites, file/limit semantics and result shape are all covered, and the output schema means return values need not be detailed. Still missing for an LLM-backed mutation tool are overwrite behavior, idempotency of re-running, and failure/partial-success handling.

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 description coverage is 0%, so the description has to compensate, and it does: 'file' is a specific filename relative to the raw directory with empty meaning whole-directory, and 'limit' is the max count when processing everything, default 10. It stops short of format details such as extensions or glob support.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: converting raw-directory source documents into wiki notes via an LLM, run manually. It also distinguishes this manual path from the watch daemon's automatic conversion, so an agent can tell it is a deliberate, on-demand ingest rather than a passive pipeline.

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?

It says this is a manual trigger that runs immediately 'when needed' on the same path as the daemon's auto conversion, which gives a clear condition for choosing it. It does not spell out exclusions (e.g. do not run concurrently with the daemon or on already-ingested files).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.