Skip to main content
Glama
Sign In
Canvas LMS MCP Server

Canvas LMS MCP Server

by bruchris
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Get Quiz Submission Answers

get_quiz_submission_answers
Read-only

Get a quiz submission's state for an IN-PROGRESS (untaken) attempt, including the student's live answer and flag per question.

Instructions

Get a quiz submission's state for an IN-PROGRESS (untaken) attempt, including the student's live answer and flag per question. For a SUBMITTED attempt (complete or pending_review), Canvas never returns the answer value or a real flag state through this endpoint — only grading state (correct) is available here. To review a submitted attempt's actual answer text, use get_quiz_question_responses instead.

Input Schema

NameRequiredDescriptionDefault
quiz_submission_idYesThe Canvas quiz submission ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.18.15
    • addedInput schema / properties / quiz_submission_id / anyOf
      Added value: +[
+  {
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "pattern": "^[1-9][0-9]{0,18}$",
+    "type": "string"
+  }
+]
    • removedInput schema / properties / quiz_submission_id / type
      Removed value: -"number"
  2. Changed1 schema field changedv1.18.11
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. First observedv1.18.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), but the description adds a non-obvious upstream API behavior the annotations cannot express: Canvas never returns the answer value or a real flag state for submitted attempts, only grading state. That warning about silently absent data is exactly the kind of behavioral disclosure that prevents misuse.

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 sentences, front-loaded with the primary use case, followed by the limitation and then the redirect. Every sentence carries distinct information with no restatement of the title or name.

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?

With no output schema, the description compensates by naming the returned fields (answer and flag per question) and what is available for submitted attempts (grading state/correct). Combined with the sibling redirect, an agent has everything needed to call it correctly and interpret the result.

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?

There is a single required parameter with 100% schema description coverage, so the schema already carries the semantics. The description adds no format, sourcing, or ID-resolution guidance beyond the schema, which is the baseline-3 case for a fully documented single param.

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 (get a quiz submission's state) and narrows the scope to IN-PROGRESS untaken attempts, listing the returned fields (live answer and flag per question). It explicitly differentiates itself from the sibling get_quiz_question_responses, so an agent can distinguish the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives both the when and the when-not: use here for untaken attempts, and for SUBMITTED attempts (complete or pending_review) this endpoint will not yield answer values or real flag state. It then names the exact alternative for that case, get_quiz_question_responses, with the condition that selects it.

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