Canvas MCP Server

Overview Schema Source Related Servers Discussions Admin

Bulk Grade Submissions

bulk_grade_submissions

Destructive

Grade multiple Canvas submissions at once with concurrent batch processing, supporting rubric-based or point-based grading and optional dry-run validation.

Instructions

Grade multiple submissions efficiently with concurrent processing.

Supports both rubric-based and simple point-based grading in batches.

Input Schema

Name	Required	Description
`grades`	Yes	Dict mapping user_id to {rubric_assessment?, grade?, comment?}. OMIT `comment` unless the instructor explicitly asked for written feedback. "Assign grade 8" means the grade ONLY. A comment is visible to the student in SpeedGrader, APPENDS a new comment on every call rather than replacing the previous one, and cannot be un-sent. Never generate a comment that merely restates the grade or narrates that grading happened.
`dry_run`	No	If True, validate without submitting (default: False)
`assignment_id`	Yes	Canvas assignment ID
`max_concurrent`	No	Max concurrent grading operations (default: 5)
`rate_limit_delay`	No	Delay between batches in seconds (default: 1.0)
`course_identifier`	Yes	Course code or Canvas ID

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

Changed17 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 / course_identifier / description
```
Added value: +"Course code or Canvas ID"
```
removedInput schema / properties / course_identifier / title
```
Removed value: -"Course Identifier"
```

addedInput schema / properties / dry_run / description

Added value: +"If True, validate without submitting (default: False)"

removedInput schema / properties / dry_run / title
```
Removed value: -"Dry Run"
```

addedInput schema / properties / grades / description

Added value: +"Dict mapping user_id to {rubric_assessment?, grade?, comment?}.\nOMIT `comment` unless the instructor explicitly asked for written\nfeedback. \"Assign grade 8\" means the grade ONLY. A comment is\nvisible to the student in SpeedGrader, APPENDS a new comment on\nevery call rather than replacing the previous one, and cannot be\nun-sent. Never generate a comment that merely restates the grade\nor narrates that grading happened."

removedInput schema / properties / grades / title
```
Removed value: -"Grades"
```

addedInput schema / properties / max_concurrent / description

Added value: +"Max concurrent grading operations (default: 5)"

removedInput schema / properties / max_concurrent / title
```
Removed value: -"Max Concurrent"
```

addedInput schema / properties / rate_limit_delay / description

Added value: +"Delay between batches in seconds (default: 1.0)"

removedInput schema / properties / rate_limit_delay / title
```
Removed value: -"Rate Limit Delay"
```

removedInput schema / title

Removed value: -"bulk_grade_submissionsArguments"

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

removedOutput schema / title

Removed value: -"bulk_grade_submissionsOutput"

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

Addedv1.0.0Jan 3, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is partly carried structurally. The description adds the two grading modes but does not warn about partial-failure behavior across concurrent batches, permission requirements, or irreversibility, which matters for a destructive bulk write.

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?

Two short sentences, front-loaded with the action and scope. 'Efficiently with concurrent processing' is mild filler since concurrency is already exposed via max_concurrent, but nothing is bloated.

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

Completeness2/5

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

For a destructive, non-idempotent bulk mutation with a nested object parameter and no output schema, the description says nothing about what is returned, how partial failures are reported, or the dry_run validation workflow. The schema documents parameters well, but the operational contract of a bulk concurrent write is left unstated.

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 coverage is 100% and the grades parameter carries extensive warnings about comment appending and visibility, so the schema does the heavy lifting. The description's mention of rubric vs point modes loosely maps to the grades dict shape but adds no format or syntax detail beyond 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?

The description names a specific verb ('grade') and resource ('multiple submissions') with batch scope, and notes both rubric-based and point-based modes. It is clearly distinguishable from single-submission tools like grade_with_rubric, though it never names a sibling explicitly.

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

Usage Guidelines2/5

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

'Grade multiple submissions efficiently' implies batch usage but gives no conditions for choosing this over grade_with_rubric or grade_with_rubric vs simple grading, no prerequisites (permissions, submission state), and no when-not guidance. The agent must infer everything about routing.

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

Deploy Server

Bulk Grade Submissions

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools