Skip to main content
Glama
Sign In
vishalsachdev

Canvas MCP Server

by vishalsachdev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Update Rubric

update_rubric
DestructiveIdempotent

Edit existing rubric criteria text and points through a preview-and-confirm flow, preserving criterion and rating IDs used by assessments.

Instructions

Safely replace an existing rubric after preview and confirmation.

Canvas updates replace the full criteria set. criteria must therefore be an ID-keyed JSON object containing every current criterion and rating, with each object's id repeated inside it. This tool does not add or remove criteria/ratings; it edits their text and points while preserving IDs used by existing assessments.

Call once without confirmation_token to receive a preview, show it to the educator, and only after they approve it call again with identical arguments and the token. Any rubric or association drift invalidates the token.

Omit free_form_criterion_comments to preserve the rubric's current setting, or pass a boolean to change it explicitly.

Input Schema

NameRequiredDescriptionDefault
titleYesRubric title (pass the current title to keep it)
criteriaYesJSON object keyed by existing criterion ID; each value repeats its "id" and carries description, points, optional long_description, and a ratings object keyed by existing rating ID in the same shape. Every current criterion and rating must be present
rubric_idYesCanvas rubric ID
course_identifierYesCourse code or Canvas ID
confirmation_tokenNoToken from the preview call; omit to preview
rubric_association_idYesThe rubric's association ID for the course or assignment, shown as "Rubric Association ID" by get_rubric
free_form_criterion_commentsNoTrue/False to change the setting; omit to keep the current one

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.15.0
  2. Removedv1.3.0
  3. Changed1 schema field changedv1.0.0
    • addedInput schema / title
      Added value: +"update_rubricArguments"
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare idempotent and destructive; the description goes well beyond by explaining that updates replace the full criteria set, that IDs must be preserved for existing assessments, and that any rubric or association drift invalidates the token. These are the mutation-specific hazards an agent cannot infer from structured fields.

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?

Front-loaded with the purpose, then organized into scope, confirmation protocol, and optional-parameter behavior. Every paragraph carries information, though a few sentences (e.g. the ID-keying restatement) echo the verbose schema field descriptions.

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?

For a destructive, token-gated mutation with no output schema, the description covers the preview/confirm cycle, full-replacement semantics, ID preservation, and drift invalidation — everything needed to avoid an irreversible mistake. Return shape of the preview is the only minor omission.

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, but the description adds meaning beyond the schema: it frames criteria as an ID-keyed object that must contain every current criterion and rating, and clarifies the semantics of omitting free_form_criterion_comments (preserve vs. change). Token drift behavior is also described here rather than in the schema.

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?

The opening sentence states a specific verb+resource ('replace an existing rubric') with a safety qualifier, and the second paragraph sharply delimits scope: it edits text and points but does not add or remove criteria/ratings. That functional boundary cleanly separates it from create_rubric and associate_rubric without needing to name them.

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?

The two-step protocol is spelled out explicitly — call once without the token to preview, get educator approval, then re-call with identical arguments plus the token. It also tells the agent when to omit free_form_criterion_comments. It stops short of naming alternatives (create_rubric, associate_rubric) for the case where the rubric doesn't yet exist.

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