Skip to main content
Glama

usb

Destructive

Manage router-attached storage and backup modem: check status, scan partitions, share or hide drives, browse files, eject safely, configure file/media/Time Machine services, and inspect 4G settings.

Instructions

USB. action=status (disks, sharing, accounts, media server, Time Machine, modem) | scan | partitions (serial) | partition (serial, uuid, enable: share/hide one partition) | eject (serial) | browse (uuid, path) | service (protocol=samba|ftp|ftpex|sftp|sftpex, enable/settings={port}) | sharing_auth | media_server | server_name | time_machine | modem (USB 4G backup internet; CRITICAL) | modem_isps.

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": "usb"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
pathNo
uuidNo
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
actionNostatus
enableNo
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main
serialNo
protocolNo
settingsNofields to change (see the matching router_catalog form)
confirm_tokenNoRequired with apply=true for CRITICAL changes: the token from the dry run (valid 5 minutes, bound to the exact plan and current router state).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds real context beyond that: apply=false is a dry run that shows plan/diff/warnings and sends nothing, apply=true executes, and CRITICAL changes need a confirm_token taken from the dry run (5-minute validity bound to the exact plan). It does not say which specific actions are destructive or require the token, which is the notable remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense run-on string with no sentence structure; the action list is front-loaded, which is good, but the inconsistent separators (pipes between actions, commas inside parentheses meaning "or") make it slower to parse than a short bulleted or sentence-based layout would be. It is compact rather than bloated, but the compression costs readability.

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?

For a 13-action, 12-parameter destructive tool with no output schema, the definition covers the action menu and the dry-run/confirm-token safety flow, which are the highest-risk unknowns. It still leaves open which actions are CRITICAL, what happens to existing shares on eject or repartition, and what status/media_server/sharing_auth return, so an agent would likely need a trial dry run for anything non-trivial.

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 only 42%, so the description must carry weight, and it does: it maps parameters to actions (serial for scan/partitions/partition/eject, uuid for partition/browse, path for browse, protocol and settings.port for service, enable for partition/service). That association is genuine meaning the schema cannot convey, since the schema lists all 12 params flatly with no action binding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a bare resource name ("USB") and then enumerates 13 action values with terse parenthetical hints ("scan", "eject (serial)", "partition (serial, uuid, enable: share/hide one partition)"). An agent can infer this is USB storage/sharing management on the router, but the overall verb+scope statement is never made explicit, and the pipe/comma notation is compressed enough that action boundaries must be reconstructed.

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 action dispatch table implicitly tells the agent which action corresponds to which task, and a few hints route it elsewhere ("see router_status 'routers'", "see the matching router_catalog form"). There is no explicit when-to-use vs when-not, no statement of prerequisites or permissions, and no guidance on choosing among similar actions such as partitions vs partition.

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