Skip to main content
Glama
bruchris

Canvas LMS MCP Server

by bruchris
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Project Grade

project_grade
Read-only

Calculate the minimum percentage needed on remaining assignments to achieve a target course grade, factoring in assignment-group weights and drop rules. Get feasibility and per-group breakdowns.

Instructions

Projects the minimum score needed on remaining assignments to reach a target course grade.

Given a target (as a percentage, e.g. 90, or a letter grade, e.g. "A") and the student's current scores, computes the minimum uniform percentage that must be earned on all remaining (not yet graded) assignments for the overall course grade to reach the target. Accounts for assignment-group weights, drop_lowest / drop_highest / never_drop rules, and the course grading scheme (for letter-grade targets and output letter mapping).

Returns:

  • minimum_pct_on_remaining: the uniform percentage needed on all remaining items.

  • feasibility: 'achievable' | 'already_secured' | 'impossible'.

  • Per-group breakdown of locked-in scores and remaining assignments.

  • A plain-language summary.

Limitations:

  • Uses a uniform-x model: the same percentage is assumed for every remaining item. This is the natural interpretation of "minimum average needed." Per-item optimization is not supported.

  • Drop rules are frozen at their current state (based on already-graded scores); which items are dropped may shift as remaining assignments are graded.

  • Late-submission penalties are not factored in.

  • V1 computes one student per call. Omit student_id to compute for the authenticated user. When CANVAS_PSEUDONYMIZE_STUDENTS is enabled, resolve the pseudonym first via resolve_pseudonym.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
course_idYesCanvas course ID to compute the grade projection for.
student_idNoCanvas user_id of the student to compute for. Omit to compute for the authenticated user. Instructors may pass any enrolled student's user_id. When CANVAS_PSEUDONYMIZE_STUDENTS is enabled, pass the numeric Canvas user_id after resolving the pseudonym via resolve_pseudonym.
target_letterNoTarget course grade as a letter (e.g. "A", "B+"). Requires the course to have a grading standard configured. Exactly one of target_percentage or target_letter must be provided. Case-insensitive.
target_percentageNoTarget course grade as a percentage (0–100). Exactly one of target_percentage or target_letter must be provided. Example: 90.0 for a 90% target.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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"
  2. Addedv1.18.3

TDQS

A4.8/5.0
Behavior4/5

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

Annotations indicate readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate that it's a read-only operation. It adds valuable context: the uniform-x model assumption, drop rules frozen at current state, and limitations like late-submission penalties not factored. These limitations are disclosed clearly, but the description doesn't detail the exact output structure (though output is described in the Returns section).

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?

The description is concise, well-structured, and front-loaded with the main purpose and key inputs. It uses clear sections (Returns, Limitations) to organize information without redundancy. Every sentence earns its place: it covers purpose, inputs, outputs, and limitations without unnecessary fluff.

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?

Given the tool's complexity (4 parameters, no output schema), the description is complete: it explains the computation model, accounts for assignment-group rules, mentions pseudonymization, and lists limitations and return values. An agent would have sufficient information to decide whether to use this tool and how to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description adds meaning beyond the schema: it explains the target parameters (target_percentage vs target_letter) and their mutual exclusivity, and notes that student_id can be omitted for the authenticated user. It also clarifies that target_letter requires a grading standard. This adds semantic value beyond basic parameter types.

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 description clearly states the tool's purpose: projecting the minimum score needed on remaining assignments to reach a target course grade. It specifies the verb ('Projects'), resource ('remaining assignments'), and target ('reach a target course grade'), and distinguishes it from siblings like 'explain_grade' and 'explain_grading_policy' by focusing on computation of required scores.

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?

The description provides explicit usage context: when to use (to compute minimum needed score), what inputs are required (target and current scores), and when not to (e.g., per-item optimization not supported, late-submission penalties not factored). It also directs to use 'resolve_pseudonym' when pseudonymization is enabled, and mentions that one student per call is supported.

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