Skip to main content
Glama

Export Course Archive

export_course_archive
Destructive

Export a complete Canvas course as an .imscc archive, wait for packaging, and download it to a permitted local folder for safekeeping before term access ends.

Instructions

Export a whole course, wait for Canvas to package it, then download the .imscc archive to local disk. Nothing in the course changes. Can take several minutes; use it before a term ends and access disappears. [NEEDS CONFIRMATION: call it once for a preview and a confirm_token, show the preview to the user, and only if they say yes call it again with the same arguments, confirm=true and that confirm_token. Apps that can ask the user directly show a confirmation 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": {
      "course_id": "<course_id>"
    },
    "name": "export_course_archive"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoSet to true together with confirm_token to carry out a request you already previewed.
dest_dirNoFolder to save into: the server's download folder (CANVAS_DOWNLOAD_DIR) or a folder inside it, such as "week1". Anywhere else is refused. Leave it out to use the download folder itself.
course_idYesCanvas course ID, a numeric string such as "12345". Get it from list_courses.
confirm_tokenNoThe one-time token from the preview. Only use it after the user has said yes.
timeout_secondsNoDefault 300

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.3.0
    • addedInput schema / properties / confirm
      Added value: +{
      +  "description": "Set to true together with confirm_token to carry out a request you already previewed.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / confirm_token
      Added value: +{
      +  "description": "The one-time token from the preview. Only use it after the user has said yes.",
      +  "type": "string"
      +}
    • changedInput schema / properties / dest_dir / description
      Previous value: -"Local folder to save into. Defaults to the server's download folder (CANVAS_DOWNLOAD_DIR)."New value: +"Folder to save into: the server's download folder (CANVAS_DOWNLOAD_DIR) or a folder inside it, such as \"week1\". Anywhere else is refused. Leave it out to use the download folder itself."
  2. Changed2 schema fields changedv1.0.2
    • changedInput schema / properties / course_id / description
      Previous value: -"Canvas course ID"New value: +"Canvas course ID, a numeric string such as \"12345\". Get it from list_courses."
    • addedInput schema / properties / dest_dir / description
      Added value: +"Local folder to save into. Defaults to the server's download folder (CANVAS_DOWNLOAD_DIR)."
  3. First observedv1.0.1

TDQS

A3.9/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: server-side packaging latency ("can take several minutes"), the preview/confirm_token gate, and the constraint that downloads land only in CANVAS_DOWNLOAD_DIR. One tension: annotations declare destructiveHint=true while the description reassures "Nothing in the course changes" — defensible because that claim is scoped to the course, but the description never clarifies the local-filesystem side (e.g., overwriting an existing .imscc in dest_dir).

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?

Front-loads the action and pipeline, then the safety note, then the confirmation protocol — a sensible order with little filler. The bracketed confirmation block is dense and reads like an inserted caveat rather than prose, but every sentence carries operational weight.

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?

There is no output schema, and the description only says an archive is downloaded to local disk without stating what is returned (file path, name, or job status) — a real gap for a long-running tool. Otherwise it covers the multi-minute wait, the confirmation gate, and the write-location restriction that an agent needs to call this correctly.

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 course_id, dest_dir, confirm, confirm_token and timeout_seconds are all already documented. The description's added value is narrow — it explains that the second call must repeat the "same arguments" — but it says nothing about timeout_seconds behavior or what dest_dir collision handling looks like. Baseline 3 for a fully documented 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 plus the pipeline stages: "Export a whole course, wait for Canvas to package it, then download the .imscc archive to local disk." The word "whole" implies scope vs. per-file tools, but no sibling is named — export_all_courses, create_content_export, get_content_export and download_all_course_files are all plausible confusions left to inference.

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 a concrete timing rationale ("use it before a term ends and access disappears") and spells out the two-step invocation protocol with the same arguments plus confirm=true and confirm_token. It stops short of explicit exclusions — it never says when to prefer create_content_export (start an export without downloading) or export_all_courses (multiple courses).

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