Skip to main content
Glama
AgenSysAdmin

AgenSysAdmin

by E13ctr0N

install_package

Destructive

Installs Debian/Ubuntu packages on a remote server via apt over SSH, optionally skipping the package list update.

Instructions

Install packages via apt on a remote server. Set update=False to skip apt update.

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": {
      "server": "<server>",
      "packages": "<packages>"
    },
    "name": "install_package"
  }
}

Input Schema

NameRequiredDescriptionDefault
serverYes
updateNo
packagesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered, and the description is consistent with it. The one genuinely additive detail is that update controls whether an apt update runs first, but the description says nothing about privilege requirements, failure behavior for unknown packages, or how long-running installs are handled.

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?

Two short sentences, zero filler, with the core action front-loaded and the one behavioral modifier placed immediately after. Nothing in the text is redundant.

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 simple three-parameter mutation, the definition is minimally sufficient: purpose plus the update toggle. Given that the tool is destructive, has no output schema, and has no schema-level parameter documentation, an agent is left guessing about privileges and result reporting, so it falls short of fully adequate.

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 0%, so the description must compensate, and it does explain the non-obvious `update` flag and its default-true behavior. However, `server` and `packages` get no treatment at all; they are left entirely to the terse schema titles, so the coverage is partial rather than complete.

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

Purpose4/5

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

The description names a specific verb (install), resource (packages), mechanism (apt), and target (remote server), which makes the tool's job unambiguous. It implicitly separates itself from the generic execute_command sibling by specifying apt, but never explicitly states that distinction.

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 by the purpose statement: the agent can infer it should call this rather than shelling out when it wants apt packages installed. There is no explicit when-to-use guidance, no prerequisite conditions (root/sudo, supported distro), and no mention of when to prefer check_updates or execute_command instead.

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