Skip to main content
Glama

disks/list

Lists block devices as a tree, showing disks, partitions, LVM/dm-crypt/RAID volumes, and mount points to inspect storage topology.

Instructions

Lists block devices as a tree (equivalent to lsblk): disks, their partitions, and LVM/dm-crypt/RAID volumes nested under the devices they're built on, with MAJ:MIN, RM, SIZE, RO, TYPE and MOUNTPOINTS. json/yaml output is the same tree under "blockdevices" (like lsblk -J), with nested "children". To check remaining free space or inode usage, use the disks/free tool. To check which folders are taking up the most space, use the disks/usage tool. (Use 'privileged: true' in containerized deployments to see the host's mount points.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
allNoInclude empty devices and RAM disks (lsblk -a)
privilegedNoRun as root - in containerized deployments, reads the host's mount table for MOUNTPOINTS
output_formatNoDesired output format (e.g. json, yaml, table, wide). Defaults to text
human_readableNoSIZE like lsblk (60G); default is bytes (lsblk -b)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does that well by explaining the tree shape, nested children in JSON/YAML, exact output columns, and the privileged caveat for containerized deployments. It stops short of covering error conditions or permission failures, but for a read-only listing tool this is strong coverage.

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?

Four sentences cover description, output structure, alternatives, and an operational caveat with no filler. The most identifying information is front-loaded and every clause earns its place.

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?

With no output schema and no annotations, the description fully compensates by explaining what is returned, how nesting works, which columns appear, and when privileged mode matters. Nothing an agent needs to select or invoke this tool correctly is missing.

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 by specifying that JSON/YAML output nests children under 'blockdevices' and mirrors lsblk -J. This gives agents practical context for output_format that the schema alone does not provide.

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 ('Lists block devices as a tree'), anchors it with 'equivalent to lsblk', and lists the exact fields returned. The description also distinguishes it from relevant siblings by naming disks/free and disks/usage for other concerns.

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?

Explicitly routes agents to disks/free for free space/inode checks and disks/usage for folder size checks, clearly marking what this tool is not for. The containerized privileged hint also prescribes a concrete condition for correct host-level results.

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