Skip to main content
Glama
Fireiscoolsolo

Canvas LMS MCP – Local Edition

by Fireiscoolsolo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Submit Assignment URL

submit_assignment_url
Destructive

Submit a website URL for a Canvas assignment that accepts URL submissions, with an optional instructor-visible comment. Preview first, then confirm to count it as a submission attempt.

Instructions

Submit a website URL for an assignment that accepts URL submissions. Your instructor sees it and it counts as a submission attempt. [IRREVERSIBLE: call without confirm=true first to preview, then re-call with confirm=true.]

Input Schema

NameRequiredDescriptionDefault
urlYesFull web address to submit, starting with https://.
commentNoComment text, visible to your instructor.
confirmNoMust be true to actually execute. Omit or set false to get a dry-run preview first.
course_idYesCanvas course ID, a numeric string such as "12345". Get it from list_courses.
assignment_idYesAssignment ID (numeric string). Get it from list_assignments or list_upcoming_assignments.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.0.2
    • changedInput schema / properties / assignment_id / description
      Previous value: -"Canvas ID (numeric string)"New value: +"Assignment ID (numeric string). Get it from list_assignments or list_upcoming_assignments."
    • addedInput schema / properties / comment / description
      Added value: +"Comment text, visible to your instructor."
    • 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 / url / description
      Added value: +"Full web address to submit, starting with https://."
  2. First observedv1.0.1

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses that the instructor sees the submission, that it counts as a submission attempt, that the action is irreversible, and that a dry-run preview via confirm is required first. That is exactly the operational context an agent needs before a destructive write.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: purpose and applicability first, consequence second, the irreversible-confirm warning bracketed and last. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, non-idempotent, open-world write with no output schema, the description covers purpose, precondition, side effects, and the safe invocation sequence. Nothing an agent needs before calling is missing.

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 100%, so the baseline is 3; the description earns above that by spelling out the confirm=false preview versus confirm=true execute semantics, which is the highest-risk parameter. It also implies the comment's instructor visibility, already documented in 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 ("Submit a website URL") plus a precondition ("an assignment that accepts URL submissions"). The URL qualifier implicitly separates it from siblings like submit_assignment_text and submit_assignment_file, though no sibling is named explicitly.

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?

"for an assignment that accepts URL submissions" gives a clear applicability condition, and the bracketed two-step confirm workflow tells the agent exactly how to proceed. It stops short of naming submit_assignment_text/file as the alternatives when URL submission isn't accepted.

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