Skip to main content
Glama
AgenSysAdmin

AgenSysAdmin

by E13ctr0N

docker_compose

Destructive

Run Docker Compose actions (up, down, restart, logs, build, and more) in a specified directory on a remote Linux server over SSH, enabling direct container stack management from AgenSysAdmin.

Instructions

Run docker compose action in a directory. action: 'up', 'down', 'restart', 'stop', 'start', 'ps', 'logs', 'pull', 'build'.

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>",
      "action": "<action>",
      "path": "<path>"
    },
    "name": "docker_compose"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
actionYes
serverYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.3/5.0
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. The description adds value by enumerating the actions, making clear that destructive operations like 'down' are in scope, but it never states what 'down' removes (containers, networks, possibly volumes) or that execution happens remotely via 'server'.

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?

Two short sentences, front-loaded with the operation and followed by the action vocabulary. The 'action: ...' fragment is terse but efficient; nothing is padded.

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

Completeness2/5

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

This is a destructive, remotely-executed mutation tool with no output schema and 0% schema description coverage. The description leaves two of three required parameters undefined and gives no indication of what is returned or what the working directory must contain (e.g., a compose file), which is inadequate for a tool of this risk level.

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 coverage is 0% and there are no enums, so the description's list of nine valid 'action' values is genuinely necessary information not available elsewhere. But the other two required parameters, 'path' and 'server', get no explanation at all — an agent cannot tell whether 'server' is a name, ID, or host, or whether 'path' is local or remote.

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 ('Run') and resource ('docker compose') and scopes it to 'in a directory', which is concrete enough to distinguish it from docker_ps, docker_logs, and execute_command. It does not explicitly state how it differs from those siblings, which keeps it below a 5.

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 enumerated actions imply the lifecycle contexts (up to start, down to tear down, logs/ps to inspect), so usage is inferable. However, there is no explicit when-to-use versus docker_ps/docker_logs/execute_command, and no warning about when 'down' is inappropriate.

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