Skip to main content
Glama

canvas_download_submissions

Downloads every file attachment for a Canvas assignment to a local folder, naming files by user ID and filename so instructors can grade or archive submissions.

Instructions

Download every file attachment for an assignment to a local folder.

Writes files to disk on the machine running this server. Each lands as <dest_dir>/<assignment_id>/<user_id>__<filename> so the owner stays attached to the file without putting a student name in a path.

FERPA: this copies student work out of Canvas onto local storage. Make sure the instructor knows where it is going and cleans it up afterwards.

Args: assignment_id: numeric assignment id. dest_dir: destination folder; defaults to CANVAS_DOWNLOAD_DIR, or ./canvas-downloads. course_id: numeric course id; defaults to CANVAS_DEFAULT_COURSE_ID. max_files: safety cap on how many files to pull (default 100).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dest_dirNo
course_idNo
max_filesNo
assignment_idYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses that files are written to disk on the server, gives the exact path template, flags a FERPA data-egress concern, and advises cleanup. Missing permissions/auth requirements and failure behavior, which keeps it from a 5.

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 core action, then layers path format and the FERPA warning; every sentence contributes. The args block is standard and readable. Slightly long but no filler.

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?

Given a filesystem-writing tool with four parameters, no annotations, and an output schema (so return values needn't be described), the description covers destination behavior, defaults, cap, and data-handling risk. Only auth/permission expectations are absent.

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%, so the description must compensate and largely does: it documents assignment_id, dest_dir (with defaults CANVAS_DOWNLOAD_DIR / ./canvas-downloads), course_id (default CANVAS_DEFAULT_COURSE_ID), and max_files (safety cap, default 100). Minor mismatch in that it calls assignment_id numeric while the schema types it as string, and it doesn't explain the env-var resolution order fully.

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 with explicit scope: downloads EVERY file attachment for an assignment into a local folder. This is immediately distinguishable from canvas_download_file (single file) and canvas_list_submissions (enumeration only) without opening any schema.

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?

The scope wording ('every file attachment for an assignment') implies the bulk-download use case and the FERPA note sets operational context, but the description never names alternatives or states when NOT to use it (e.g., use canvas_download_file for a single file, canvas_list_submissions to preview). Usage is inferable rather than explicit.

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