Skip to main content
Glama

Get Feedback

get_feedback
Read-only

Fetch a course's recently graded work with scores, instructor comments, and rubric results to identify error patterns and guide targeted practice or review.

Instructions

Returns the student's recently graded work in a course with scores, instructor comments, and rubric results. Use it to find patterns in what went wrong and turn them into specific things to practice or review.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "course_id": "<course_id>"
    },
    "name": "get_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many graded items, most recent first
course_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.11.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description usefully adds the payload contents and the 'recently graded' recency framing, but says nothing about whose data is returned (the authenticated student only?), what happens with no graded work, or how many items come back by default.

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 tight sentences with the resource and payload front-loaded, followed by a short actionable use case. Nothing is redundant, though the second sentence is advisory rather than specification and could be trimmed without losing meaning.

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?

With no output schema, the description carries the burden of describing returns, and it does list the three main response components (scores, comments, rubric). Remaining gaps — course_id provenance, default/limit behavior, empty-result handling — are modest for a two-parameter read tool.

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 only 50%: the 'limit' parameter is documented in the schema, but 'course_id' has no description at all. The phrase 'in a course' weakly signals that course_id scopes the call, yet the description never says the course_id must come from list_courses or that it is an integer identifier, so it only partially compensates.

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?

States a specific verb and resource: 'Returns the student's recently graded work in a course,' and enumerates what comes back (scores, instructor comments, rubric results). It is clearly a graded-work/feedback retrieval tool rather than an assignment or review-queue tool, but it never explicitly contrasts itself with siblings like get_assignment or get_review_stats.

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

Usage Guidelines3/5

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

The second sentence gives one motivating use case ('find patterns in what went wrong and turn them into specific things to practice or review'), which implies when to reach for it. There is no when-not guidance, no prerequisites, and no mention of which sibling to use for a single assignment's details versus this aggregate feedback view.

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