submit_rubric_assessmentSubmit rubric scores and comments for each criterion to grade a submission.
Submit a rubric assessment with scores and comments for each criterion.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Array of criterion assessments | |
| course_id | Yes | The Canvas course ID | |
| association_id | Yes | The rubric association ID |
Changes observed during successful MCP inspections.
v1.18.11Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"v1.18.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only restates the action implied by the title ('submit'), adding no behavioral detail about side effects beyond the annotations. It does not explain that idempotentHint and destructiveHint are relevant, what overwrites or post-submission behavior occur, or any rate/auth requirements. With only two-sentence descriptions and no additional context, the description captures all of the behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, straightforward sentence with no filler or repetition. It gets directly to the action and payload, making it easy to scan and absorb.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a non-nested but moderately complex structure (array of criterion objects) and no output schema. The description fails to clarify the purpose of association_id, whether this targets a submission, a peer review, or some other entity, and what the after-effects are. An agent gets the objective but not enough surrounding context to understand when this submission is valid or what it means in the Canvas workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline 3 applies. The description does not add anything beyond what the schema already says about course_id, association_id, or the data array items. It confirms that scores and comments are per criterion, but that is already captured in the parameter definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Submit a rubric assessment,' and it enumerates the content (scores and comments per criterion). It is clear enough to distinguish from sibling read-only tools like get_rubric_assessment, though it does not explicitly contrast with closely related grading tools like grade_submission or score_quiz_question.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance about when to use this tool versus alternatives such as grade_submission, comment_on_submission, or score_quiz_question. No prerequisites, constraints, or exclusions are provided, so an agent must infer trading-off between related tools from names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.