Skip to main content
Glama
avaazquezz

Qdrant RAG Build

by avaazquezz

ingest_file

Upload a single local PDF, DOCX, XLSX, PPTX, MD, HTML, CSV, or TXT file into a collection. The file is processed with format-specific quality handling to ensure clean, searchable content for RAG.

Instructions

Ingests a single local file (PDF, DOCX, XLSX, PPTX, MD, HTML, CSV, or TXT) into a collection, with format-specific quality processing. Use this for one file at a time; use ingest_directory for a whole folder.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
collectionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
doc_idYes
collectionYes
source_pathYes
chunks_createdYes
discard_reasonsYes
pages_discardedYes
duplicates_foundYes
Behavior3/5

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

The annotations already signal that this is a write operation that is not destructive. The description adds that ingestion involves format-specific quality processing, but it does not explain what this processing does, whether the collection must already exist, or whether an existing document is replaced or duplicated. The added context is modest rather than rich.

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?

Two tight, front-loaded sentences: the main action and supported formats come first, and the single-file restriction is placed before the alternative tool. No redundant or filler wording is present.

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

Completeness4/5

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

The core information for calling the tool is present: file type scope, one-file usage, and the destination collection. The output schema covers return expectations. It would be even better if it specified file path constraints, collection preconditions, or the nature of the quality processing, but the definition is not missing the critical invocation information.

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

Parameters3/5

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

With 0% schema coverage, the description needs to define the parameters. It implicitly maps 'path' to a local file path and 'collection' to the destination collection, which helps, but it omits operational details such as whether the path must be absolute, whether the collection must exist, or how collection names are specified.

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?

Clearly states the verb 'ingests' and the exact resource: a single local file from an explicit list of formats into a collection. The scope is narrowed to one-at-a-time ingestion, which also differentiates it from ingest_directory even though other sibling ingest tools are not named.

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?

Gives an explicit usage boundary: 'Use this for one file at a time' and names the folder-level alternative ingest_directory. It does not explicitly mention ingest_text or ingest_url as alternatives for non-file inputs, but the enumerated file formats plus 'local file' make the intended use reasonably clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/avaazquezz/RAG-Build'

If you have feedback or need assistance with the MCP directory API, please join our Discord server