ufsc-moodle-mcp

Visão consolidada em lote de entregas, grupos, notas, feedbacks, workflow e cobertura da tarefa

get_assignment_grading_overview

Read-onlyIdempotent

Retrieves a consolidated grading overview for a Moodle assignment, including groups, members, submissions, grades, feedback, workflow status, visibility, and detected inconsistencies.

Instructions

Recupera em uma única operação consolidada todo o panorama de avaliação de uma tarefa do Moodle: metadados da tarefa, grupos efetivos do projeto (excluindo grupos gerais de turma), integrantes confirmados (sem docentes), entregas coletivas e individuais com arquivos deduplicados, notas individuais e agregadas por grupo (fully_graded, partially_graded, not_graded, inconsistent), comentários de avaliação existentes (gradingFeedbackComments), estados de workflow e visibilidade, cobertura percentual e inconsistências detectadas.

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": {
      "assignmentId": "<assignmentId>"
    },
    "name": "get_assignment_grading_overview"
  }
}

Input Schema

Name	Required	Description
`fresh`	No	Se true, ignora caches temporários e força releitura direta do Moodle.
`limit`	No	Quantidade máxima de grupos/itens retornados por página (padrão: 200).
`cursor`	No	Cursor numérico opcional para paginação (nextCursor da chamada anterior).
`courseId`	No	ID opcional da disciplina (resolvido automaticamente quando omitido).
`assignmentId`	Yes	ID da tarefa (assignmentId) no Moodle.
`includeGrades`	No	Se true (padrão), inclui notas individuais, nota agregada comum e divergências.
`includeGroups`	No	Se true (padrão), retorna a lista detalhada de grupos da tarefa.
`includeMembers`	No	Se true (padrão), inclui os integrantes e suas avaliações individuais em cada grupo.
`includeFeedback`	No	Se true (padrão), inclui comentários da avaliação existentes (gradingFeedbackComments) e hash SHA-256.
`includeWorkflow`	No	Se true (padrão), inclui estados de workflow da avaliação.
`includeVisibility`	No	Se true (padrão), inclui estado de publicação e visibilidade para os estudantes.
`includePersonalData`	No	Se true, inclui e-mail institucional dos estudantes (padrão: false).
`includeSubmissionComments`	No	Se true, consulta também comentários da entrega (assignsubmission_comments) de cada submissão enviada (padrão: false para máxima velocidade).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.1Nov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds real behavioral context beyond them: general course groups are excluded, teachers are excluded from members, files are deduplicated, and grade state is aggregated into categories (fully_graded, partially_graded, not_graded, inconsistent) with a coverage percentage and inconsistency detection. It does not disclose permission requirements or performance cost of the heavier flags, which keeps it just below a 5.

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?

Purpose is front-loaded in the first clause and every element of the long enumeration carries information rather than filler. The weakness is structure: the whole definition is a single run-on sentence with a deeply nested list, which would read far better as a short lead plus bullets, and there is some redundancy with the title.

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 13 parameters and no output schema, the description carries the burden of describing the return payload and does so thoroughly by naming every included section, which is exactly what an agent needs to decide which include* flags to set. Gaps remain around failure modes (assignment not found, courseId mismatch) and the cost trade-off of fresh/includeSubmissionComments, but nothing essential for calling it correctly is missing.

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 description coverage is 100% and every parameter, including defaults for includePersonalData and includeSubmissionComments, is documented in the schema itself, so the baseline is 3. The description only loosely maps to parameters by describing what the group/member/feedback sections contain (effective groups, members without teachers, deduplicated files), which adds modest meaning but no syntax, format, or interaction detail beyond 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 description opens with a specific verb and resource ('Recupera em uma única operação consolidada todo o panorama de avaliação de uma tarefa do Moodle') and then enumerates exactly what is bundled: assignment metadata, effective project groups, confirmed members, collective and individual submissions with deduplicated files, individual and aggregated grades, feedback comments, workflow/visibility states, coverage percentages and detected inconsistencies. That enumeration makes it unmistakable against siblings such as get_submissions or prepare_grading_batch, which return single facets rather than the consolidated panorama.

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?

Usage is only implied: 'em uma única operação consolidada' signals this is the one-shot alternative to piecing the data together from multiple calls, and the include* flags imply a way to trim scope. But no sibling is named and no explicit when-not condition is given (e.g. use get_submissions for a single student, or prepare_grading_batch when you intend to write grades). The agent has to infer the routing.

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