Skip to main content
Glama

iam_policy_review

Read-onlyIdempotent

Inspect AWS, Azure, or GCP IAM policies to flag overly broad permissions and highlight grants needing review before approval.

Instructions

Inspect an IAM document for broad grants: AWS policy JSON (default), Azure custom role definition or Google Cloud IAM policy bindings (provider). Heuristic only; the provider analyzers are authoritative.

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": {
      "policy": "<policy>"
    },
    "name": "iam_policy_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
policyYes
providerNoaws

Output Schema

NameRequiredDescriptionDefault
kindNo
sourcesNo
findingsNo
providerNo
validatedNo
limitationNo
limitationsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • changedInput schema / required
      Previous value: -[
      -  "policy",
      -  "provider"
      -]New value: +[
      +  "policy"
      +]
  2. First observedv0.4.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds meaningful context on top: the analysis is heuristic and non-authoritative, which warns the agent not to present findings as definitive. It does not mention input size limits or how findings are ranked, and return values are covered by the output schema.

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 sentences, no filler. The action and scan target come first, provider dialects second, and the heuristic caveat closes it — a well front-loaded structure for a short definition.

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?

With read-only annotations covering safety and an output schema covering results, the description supplies what structure does not: the accepted input dialects and the non-authoritative nature of the analysis. It remains thin on what 'broad grants' means concretely, but nothing required to invoke the tool correctly is absent.

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 has to carry the parameter burden. It does well on 'provider', mapping each enum value to the expected document dialect and confirming AWS is the default; for 'policy' it only indicates the document family, not the expected object shape or what patterns (e.g. wildcard actions) trigger findings, which matters for a free-form nested object.

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?

States a specific verb ('inspect') and resource ('IAM document') and names the concrete signal it looks for ('broad grants'), which is more than a restatement of the name. It also enumerates the three input dialects (AWS policy JSON default, Azure custom role definition, GCP IAM policy bindings). It stops short of naming which sibling tool to prefer for deeper analysis, referring only vaguely to 'the provider analyzers'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause 'Heuristic only; the provider analyzers are authoritative' is real usage guidance: it tells the agent this is a quick first-pass screen, not a compliance determination, and points toward authoritative checks. What's missing is an explicit named alternative among the sibling tools or a stated condition such as 'use before/after X'.

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