Skip to main content
Glama
mcp-server-redmine

mcp-server-redmine

by jesusr00

redmine_download_attachment

Download a Redmine attachment by numeric ID to retrieve its content. Raster images return as viewable images, text files return inline, and large or unsupported files return metadata.

Instructions

[Alpha] Download a Redmine attachment by its numeric ID (find IDs with redmine_get_issue using include=attachments). Raster images (png, jpeg, gif, webp) are returned as viewable image content; text files, including JSON and SVG, are returned inline (long ones truncated); other types, images over 3.5 MB, and text over 5 MB return metadata instead.

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": "redmine_download_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
attachment_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.1

TDQS

A4.3/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden and does so well: it discloses return modality per type (raster images as viewable content, text inline with truncation, everything else as metadata) and concrete size cutoffs (3.5 MB images, 5 MB text). What it omits is permission/auth requirements and failure behavior for nonexistent attachments.

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?

Purpose and ID-discovery hint are front-loaded, then return behaviors follow in a single dense but scannable sentence. The size thresholds and type list are information-dense rather than padded; the only soft spot is the vague 'long ones truncated' phrasing.

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?

For a one-parameter read tool with no output schema, the description covers the otherwise invisible behavior: polymorphic return types and size-based fallback to metadata. Permission requirements and error responses remain undocumented, which is the notable remaining gap.

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 coverage is 0% and the schema only constrains the integer to a positive 64-bit value, so the description must add meaning. It does: the parameter is an attachment's numeric ID and where to source it, which is the key semantic an agent needs before calling.

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?

States a specific verb and resource ('Download a Redmine attachment by its numeric ID'), which cleanly separates it from redmine_upload_attachment and from issue-reading siblings. The '[Alpha]' prefix and the parenthetical pointing to redmine_get_issue as the ID source make the function unambiguous.

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 explicit routing guidance for the missing prerequisite: obtain IDs via redmine_get_issue with include=attachments. It does not state when to prefer a different retrieval path (e.g. redmine_list_files) or what to do on an invalid/expired ID, but the primary when-to-use context is present.

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