Skip to main content
Glama

Disks, storage pools and volumes

nas_storage_info
Destructive

Read NAS storage state to check disk health and temperature, volume capacity and free space, and pool RAID status. Use disks and pools for health, volumes for remaining space.

Instructions

Read storage state. kind "disks" lists internal disks with health and temperature; "volumes" lists storage volumes with total and used space, mount point and warnings; "pools" lists storage pools with RAID level, status and member disks. To answer "are my disks healthy" check both disks and pools; for "how much space is left" use volumes (free = total - used). Sizes are strings in bytes, and a total of "0" means not mounted, so do not compute usage from it. A temperature of 0 means unreadable, not zero degrees. Disk status UNSUPPORTED means health cannot be determined, which is not the same as healthy. A pool reported as GOOD can still contain a missing or unhealthy disk, so also read disks[].status; a missing disk does not make the call fail. kind "smart" returns raw SMART attributes for every disk: this is sensitive diagnostic data, needs admin access and a confirmation, and should be requested only when the user explicitly asks for it. Serial numbers are masked unless show_serial is true, which is likewise only for an explicit request. Pools and volumes cannot be created, expanded or deleted through this server.

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": {
      "kind": "<kind>"
    },
    "name": "nas_storage_info"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesWhat to read.
show_serialNoFor "disks" and "smart": show real serial numbers.
confirm_tokenNoToken returned by the preview call. Omit it to get a preview; nothing changes without it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior1/5

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

The description frames the tool as a passive read ("Read storage state", "cannot be created, expanded or deleted through this server") while annotations declare readOnlyHint=false and destructiveHint=true. It never explains the confirm_token/preview flow that the schema advertises, so the destructive capability is left unexplained and effectively contradicted. The rich sentinel-value guidance (0 total, temperature 0, UNSUPPORTED, GOOD pool with a dead disk) is genuinely valuable but does not resolve the core inconsistency.

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-loaded with the one-line purpose, then organized per kind plus interpretation caveats; every sentence carries operational information. It is long and prose-dense - bullet-per-kind or a split between usage and caveats would scan faster - but nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of describing return fields and sentinel values, which it does well. However, a tool carrying destructiveHint=true and a confirm_token parameter only half-explains its own contract, since the confirmation lifecycle is never described.

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 baseline is 3; the description earns a point by adding real semantics the terse enum description ("What to read.") lacks - what each kind returns, how to combine them, and why show_serial is gated. It adds nothing about confirm_token, leaving one parameter purely to 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?

States a concrete verb+resource ("Read storage state") and then enumerates the four readable kinds with their returned fields, which lets an agent distinguish this storage tool from siblings like nas_network_info or nas_system_info without opening the schema.

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 routing rules tied to user questions ("are my disks healthy" -> disks + pools; "how much space is left" -> volumes), and explicitly restricts smart to explicit user requests, including an exclusion for show_serial. When-not guidance is present and specific.

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