Skip to main content
Glama

learnjcu_download_attachment

Downloads a course content attachment to the local Downloads/learnjcu folder and returns the saved file path for direct access.

Instructions

Download a file from a content item (an attachment id, or an "embedded-N" id from learnjcu_get_content) into the local Downloads/learnjcu folder and return its path.

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": {
      "courseId": "<courseId>",
      "contentId": "<contentId>",
      "attachmentId": "<attachmentId>"
    },
    "name": "learnjcu_download_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
accountNoSaved account to use (see learnjcu_list_accounts). Only needed when several accounts are saved and the user has not chosen one yet.
courseIdYesCourse primary id like "_123456_1" (from learnjcu_list_courses), a subject code like "BU2001", or the full course code
contentIdYes
attachmentIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, so the write/network nature is already signalled. The description adds the genuinely useful detail that files land in Downloads/learnjcu and the path is returned, but says nothing about overwrite behavior, naming collisions, size limits, or auth/account requirements.

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?

A single front-loaded sentence that carries the action, the id formats, the destination, and the return value with no filler. The parenthetical is slightly dense but each clause earns its place.

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 download tool with no output schema, the description states where the file goes and that a path is returned, which covers the essential return behavior. The remaining gap is contentId's meaning and any overwrite/error semantics.

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 coverage is 50%, and the description compensates for the hardest parameter by defining attachmentId's accepted formats and where the embedded-N ids come from. However, contentId has no schema description and no explanation in the description, and the interaction with the optional account parameter is left to the schema.

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 file from a content item), names the destination folder, and specifies the return value (its path). It also disambiguates the accepted id forms, so an agent can tell it apart from learnjcu_get_content, which it references as the source of embedded ids.

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?

Explains the prerequisite workflow: the attachment id or an "embedded-N" id must come from learnjcu_get_content. There is no explicit statement of when not to use it or of a competing download alternative, but the sourcing guidance is concrete enough to select and call it correctly.

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