Skip to main content
Glama
Canvas LMS MCP – Remote Edition

Canvas LMS MCP – Remote Edition

Submit Peer Review

submit_peer_review
Destructive

Submit a classmate’s peer review with a comment and optional rubric scores; preview first, then confirm to post it. Get the student ID from your peer review list.

Instructions

Submit your peer review of a classmate's work: a comment and, optionally, rubric scores. The classmate and instructor can see it. Get student_id from list_my_peer_reviews. [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>",
      "assignment_id": "<assignment_id>",
      "student_id": "<student_id>",
      "comment": "<comment>"
    },
    "name": "submit_peer_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
commentYesYour review comment. The classmate and your instructor can see it.
confirmNoSet to true together with confirm_token to carry out a request you already previewed.
course_idYesCanvas course ID, a numeric string such as "12345". Get it from list_courses.
student_idYesThe student whose work you are reviewing
assignment_idYesAssignment ID (numeric string). Get it from list_assignments or list_upcoming_assignments.
confirm_tokenNoThe one-time token from the preview. Only use it after the user has said yes.
rubric_assessmentNoOptional rubric scores keyed by criterion ID, e.g. {"_1234": {"points": 4, "comments": "Clear thesis"}}. Get criterion IDs from get_rubric.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.0
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to actually execute. Omit or set false to get a dry-run preview first."New value: +"Set to true together with confirm_token to carry out a request you already previewed."
    • 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"
      +}
  2. Changed4 schema fields changedv1.1.3
    • 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: +"Your review comment. The classmate and your instructor can see it."
    • 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 / rubric_assessment / description
      Added value: +"Optional rubric scores keyed by criterion ID, e.g. {\"_1234\": {\"points\": 4, \"comments\": \"Clear thesis\"}}. Get criterion IDs from get_rubric."
  3. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, and the description adds genuinely non-redundant context: the review is visible to the classmate and instructor, and the call is two-phase (preview returns a confirm_token, then a repeat call with confirm=true commits). It does not explain why the operation is flagged destructive (e.g. whether resubmitting overwrites an existing review), which is the one behavioral gap.

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, audience, ID provenance and the confirmation protocol are front-loaded and each sentence carries information. The bracketed confirmation block is dense and reads like an internal annotation ('[NEEDS CONFIRMATION: ...]'), which slightly hurts polish but not comprehension.

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 7-parameter destructive write with a nested rubric object and no output schema, the definition covers the critical unknowns: what gets published, to whom, where IDs come from, and exactly how to run the confirm handshake. Only the overwrite/re-submission semantics and the preview payload contents are left unspecified.

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 all seven parameters including the nested rubric_assessment and the confirm/confirm_token pair are already documented in the schema. The description adds only the provenance hint for student_id and the optionality of rubric scores, which the schema also states, so baseline 3 applies.

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 ('Submit your peer review of a classmate's work') plus the payload shape (a comment and optional rubric scores), and the visibility note ('The classmate and instructor can see it') further disambiguates it from sibling submission tools like submit_assignment_text. An agent can distinguish it from every other submit_* sibling without opening the schema.

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 prerequisite routing ('Get student_id from list_my_peer_reviews') and a full two-phase invocation protocol for the confirmation step. It does not name when NOT to use it (e.g. when the review is already submitted, or how to edit an existing review), so it stops short of full when/when-not coverage.

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