Skip to main content
Glama

listar_arquivos

Read-only

Mostra o que existe num módulo (ou em toda a pasta de estudos), para saber o que ler com ler_material. Use para resumir um módulo, montar um quiz ou um plano de estudo.

Instructions

Mostra o que existe num módulo (ou em toda a pasta de estudos), para saber o que ler com ler_material. Use para resumir um módulo, montar um quiz ou um plano de estudo. Até 100 arquivos, lista cada um com tipo e tamanho; acima disso, mostra as subpastas com quantos arquivos cada uma tem e o começo do README dela (chame de novo com uma subpasta para ver os arquivos dela).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "listar_arquivos"
  }
}

Input Schema

NameRequiredDescriptionDefault
tiposNoSó estes tipos: anotacoes, pdf, codigo. Padrão: todos
moduloNoPasta do módulo, como retornada por listar_modulos (ex.: curso/modulo03), ou uma subpasta dele. Vazio: toda a pasta de estudos

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.0
    • changedInput schema / properties / modulo / description
      Previous value: -"Pasta do módulo, como retornada por listar_modulos (ex.: curso/modulo03). Vazio: toda a pasta de estudos"New value: +"Pasta do módulo, como retornada por listar_modulos (ex.: curso/modulo03), ou uma subpasta dele. Vazio: toda a pasta de estudos"
    • changedOutput schema / (root)
      Previous value: -{
      -  "$schema": "http://json-schema.org/draft-07/schema#",
      -  "additionalProperties": false,
      -  "properties": {
      -    "arquivos": {
      -      "items": {
      -        "additionalProperties": false,
      -        "properties": {
      -          "arquivo": {
      -            "description": "Caminho para usar em ler_material",
      -            "type": "string"
      -          },
      -          "kb": {
      -            "description": "Tamanho em KB",
      -            "type": "number"
      -          },
      -          "tipo": {
      -            "enum": [
      -              "anotacoes",
      -              "codigo",
      -              "pdf"
      -            ],
      -            "type": "string"
      -          }
      -        },
      -        "required": [
      -          "arquivo",
      -          "tipo",
      -          "kb"
      -        ],
      -        "type": "object"
      -      },
      -      "type": "array"
      -    },
      -    "total": {
      -      "description": "Total de arquivos encontrados (a lista mostra até 100)",
      -      "type": "number"
      -    }
      -  },
      -  "required": [
      -    "arquivos",
      -    "total"
      -  ],
      -  "type": "object"
      -}New value: +null
  2. Addedv1.3.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral detail the agent could not otherwise know: the 100-file threshold, the per-file payload (type and size), and the degraded aggregate mode with subfolder counts plus README excerpts that requires a follow-up call. That is exactly the extra context annotations cannot carry.

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-loads the core purpose and the ler_material link before the volume-dependent behavior, and every clause carries information. The final sentence is a long run-on covering two ideas, which slightly hurts readability but wastes no words.

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?

There is no output schema, so the description must describe return shape itself — and it does, covering both the enumerated listing and the aggregated subfolder view. For a two-parameter read-only tool with safe annotations, nothing an agent needs to call 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%, with both parameters fully documented including the empty-modulo meaning and the accepted types. The description only loosely restates the module-vs-whole-folder behavior and adds no syntax or enum detail beyond the schema, so baseline 3 applies.

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?

States a specific verb and resource: listing what exists inside a module or the whole study folder. It immediately differentiates itself from siblings by scoping the result as input for ler_material, and the schema ties 'modulo' back to listar_modulos output, so an agent can place it in the workflow without opening another definition.

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?

Gives explicit use cases (summarize a module, build a quiz or study plan) and names the downstream sibling (ler_material) plus the fallback (call again with a subfolder). It also states the condition that selects the alternate behavior (more than 100 files), leaving nothing to inference.

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