Skip to main content
Glama

audit_compose

Review a docker-compose file for security and reliability (paid, metered): unpinned images, exposed databases/admin panels, plaintext secrets, Docker socket mounts, privileged containers, missing volumes, restart policies and health checks. Send the whole file as text.

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": {
      "compose_yaml": "<compose_yaml>"
    },
    "name": "audit_compose"
  }
}

Input Schema

NameRequiredDescriptionDefault
compose_yamlYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose two non-obvious behavioral traits — the call is paid/metered, and the whole file must be passed as text rather than a path — which is real added value. It stays silent on whether the file is modified, rate/quota limits beyond 'metered', and failure behavior on malformed YAML.

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?

The audit surface is front-loaded in the first clause, and the cost/pass-as-text constraints land before the agent commits. The long middle enumeration of checks is dense but each item is a distinct, decision-relevant finding category, so it earns its space; only minor tightening is possible.

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

Completeness4/5

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

For a one-parameter tool with an output schema (so return values need no explanation), the definition covers the input contract and the cost model adequately. The remaining gap is error/edge-case behavior — oversized files, non-YAML input — which an agent might need but can likely discover at call time.

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 description coverage is 0% for the single parameter, so the schema alone leaves compose_yaml ambiguous (path vs. content). 'Send the whole file as text' resolves that ambiguity directly, which is exactly the compensation needed. It stops short of stating size limits or encoding expectations.

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 ('Review a docker-compose file') and then enumerates exactly what it inspects: unpinned images, exposed databases/admin panels, secrets, socket mounts, privileged containers, volumes, restart policies, health checks. That enumeration makes it unmistakable against siblings like audit_backup_plan or audit_grant_budget, which target entirely different artifacts.

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?

'Send the whole file as text' is an actionable input instruction and '(paid, metered)' signals a cost boundary before invoking. However, it never says when not to use it, whether it is safe to run repeatedly on the same file, or what to do instead if the file is not a compose file — usage is only implied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources