Canvas MCP Server

Overview Schema Source Related Servers Discussions Admin

Grade With Rubric

grade_with_rubric

Destructive

Submit student grades for Canvas assignments using rubric criteria, mapping each criterion to points and optional ratings or comments. Use rubric IDs from the assignment to ensure accurate grading.

Instructions

Submit grades using rubric criteria.

Criterion IDs often start with an underscore (e.g., "_8027"); look up criterion and rating IDs with get_rubric rather than guessing them. The rubric must be attached to the assignment and configured for grading (use_for_grading=true).

Input Schema

Name	Required	Description
`comment`	No	Optional overall comment. OMIT it unless the instructor explicitly asked for written feedback -- "grade this with the rubric" means the grade only. It is visible to the student in SpeedGrader, APPENDS rather than replaces on each call, and cannot be un-sent. Never generate one that merely restates the grade or narrates that grading happened.
`user_id`	Yes	Canvas user ID of the student
`assignment_id`	Yes	Canvas assignment ID
`course_identifier`	Yes	Course code or Canvas ID
`rubric_assessment`	Yes	Dict mapping criterion_id to {points (required), rating_id?, comments?}

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.10.0Aug 20, 2026

changedOutput schema / (root)

Previous value: -{
-  "properties": {
-    "result": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "type": "object",
-  "x-fastmcp-wrap-result": true
-}New value: +null

Changed15 schema fields changedv1.8.0Aug 10, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / assignment_id / description
```
Added value: +"Canvas assignment ID"
```
removedInput schema / properties / assignment_id / title
```
Removed value: -"Assignment Id"
```

addedInput schema / properties / comment / description

Added value: +"Optional overall comment. OMIT it unless the instructor\nexplicitly asked for written feedback -- \"grade this with the\nrubric\" means the grade only. It is visible to the student in\nSpeedGrader, APPENDS rather than replaces on each call, and\ncannot be un-sent. Never generate one that merely restates the\ngrade or narrates that grading happened."

removedInput schema / properties / comment / title
```
Removed value: -"Comment"
```
addedInput schema / properties / course_identifier / description
```
Added value: +"Course code or Canvas ID"
```
removedInput schema / properties / course_identifier / title
```
Removed value: -"Course Identifier"
```

addedInput schema / properties / rubric_assessment / description

Added value: +"Dict mapping criterion_id to {points (required), rating_id?, comments?}"

removedInput schema / properties / rubric_assessment / title
```
Removed value: -"Rubric Assessment"
```
addedInput schema / properties / user_id / description
```
Added value: +"Canvas user ID of the student"
```
removedInput schema / properties / user_id / title
```
Removed value: -"User Id"
```

removedInput schema / title

Removed value: -"grade_with_rubricArguments"

removedOutput schema / properties / result / title
```
Removed value: -"Result"
```

removedOutput schema / title

Removed value: -"grade_with_rubricOutput"

addedOutput schema / x-fastmcp-wrap-result
```
Added value: +true
```

Changed3 schema fields changedv1.0.0Jan 3, 2026
- addedInput schema / properties / rubric_assessment / additionalProperties
```
Added value: +true
```
- changedInput schema / properties / rubric_assessment / type
```
Previous value: -"string"New value: +"object"
```
- addedInput schema / title
```
Added value: +"grade_with_rubricArguments"
```
First observedSep 27, 2025

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds the prerequisite state that must hold before the call succeeds, which is behavior beyond the annotations. It does not itself state whether a prior assessment is overwritten or what happens on repeat calls, leaving part of the destructiveness implicit.

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 short sentences plus a parenthetical example, front-loaded with the action and followed by the failure-prone details. Nothing is redundant.

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 destructive, nested-object mutation with no output schema, the description covers preconditions, ID resolution, and (via the schema) the comment side effect. The gap is that assess-then-reassess semantics are never explained in the description itself.

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 an extra point by warning that criterion IDs often begin with an underscore and that rating IDs must be resolved via get_rubric. That is real guidance the schema cannot express.

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?

The description opens with a specific verb and resource ('Submit grades using rubric criteria'), which is far more precise than the sibling bulk_grade_submissions or the read-only get_rubric_assessment. It doesn't explicitly name the sibling it differs from, though the get_rubric reference implies the division of labor.

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?

It supplies two concrete preconditions (the rubric must be attached to the assignment and configured with use_for_grading=true) and routes the agent to get_rubric for ID lookup instead of guessing. It stops short of stating exclusions such as when to prefer bulk_grade_submissions.

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

Deploy Server

Grade With Rubric

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools