Skip to main content
Glama

Ravi CI Guard: GitHub Actions security audit

See a full audit on a sample (free)

audit_sample
Read-only

FREE demo. Runs the real audit_workflows on a built-in SAMPLE workflow (a pull_request_target preview job) that contains typical mistakes on purpose: pwn request, script injection, missing permissions, retired runner, unpinned and deprecated actions. Shows exactly what audit_workflows returns (findings with evidence/why/fix, SHA pins, patches) before you buy a pass. Takes no arguments; it never audits your own code.

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": "audit_sample"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds what the annotations cannot — that it is free, argument-free, operates on a fixed built-in workflow, and returns findings with evidence/why/fix, SHA pins and patches. The only soft tension is openWorldHint=true against a tool that touches no external systems, but that is a minor mismatch rather than a contradiction.

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?

Three sentences, front-loaded with the key distinction ('FREE demo' / 'built-in SAMPLE'), then the return shape, then the no-argument caveat. The 'FREE'/'before you buy a pass' framing is commercial tinged but does convey a real usage constraint, so little is wasted.

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

Completeness5/5

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

For a no-argument demo tool with no output schema, the description fully covers what it runs, what it returns, and what it does not do. An agent has everything needed to call it correctly and to interpret the result.

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?

There are zero parameters and the description explicitly confirms 'Takes no arguments', so an agent will not hunt for inputs. Baseline for a 0-param tool is 4, and the explicit statement is a small addition over the schema's empty properties.

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 ('Runs the real audit_workflows on a built-in SAMPLE workflow') and immediately scopes it away from the sibling by naming the sample: a pull_request_target preview job. The content of the sample (pwn request, script injection, missing permissions, unpinned actions) makes it unmistakable versus audit_workflows.

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 when-to-use ('before you buy a pass') and an explicit exclusion ('it never audits your own code'), which implicitly routes the agent to audit_workflows for real code. Nothing is left to inference about which tool to pick.

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