Skip to main content
Glama
Sign In
ragflow-kb-mcp

ragflow-kb-mcp

by feci
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

ragflow_download_agent_attachment

Read-only

Downloads an agent attachment by ID, returning text content directly or binary data as base64 when requested.

Instructions

Download an agent attachment. Text comes back as text; binary content as base64 on request.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "attachment_id": "<attachment_id>"
    },
    "name": "ragflow_download_agent_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
extNoFile extension such as pdf or txt, used for the content type
max_charsNoReturn at most this many characters of text
attachment_idYesAttachment ID, e.g. a file an agent produced or one uploaded
include_base64NoReturn binary content as base64 (up to 5 MB)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real return-behavior context — text returned as text, binary returned as base64 only on request — but omits the 5 MB base64 cap and the truncation behavior of max_chars, which are behaviorally important for a download 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?

Two short sentences, front-loaded with the action, with no filler. The second sentence is slightly compressed to the point of vagueness ('on request' rather than naming the flag), a minor cost.

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?

An output schema exists, so return values need not be spelled out, and the one required parameter plus three well-described optional ones leave little ambiguity. What is missing is the interplay between include_base64 and max_chars (which wins, what gets truncated), the one real gap for correct invocation.

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?

Schema description coverage is 100%, so all four parameters are documented in structured data and baseline 3 applies. The phrase 'on request' loosely gestures at include_base64 and the text/binary split hints at ext, but adds no format, default, or limit detail beyond the schema.

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?

States a specific verb and resource ('Download an agent attachment'), and the qualifier 'agent' helps distinguish it from ragflow_download_file and ragflow_download_document in the sibling list. However, it never explicitly contrasts itself with those two near-identical download tools, so an agent must infer the distinction from the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'agent attachment' suggests it applies to files produced by agents or uploaded as attachments, which implicitly excludes dataset documents. There is no explicit when-to-use or when-not statement, and no routing to ragflow_download_file or ragflow_get_commit_file_content as alternatives.

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

Deploy Server

Other Tools