Skip to main content
Glama

get_acl_posture

Read-only

Inspect ACL posture for a ServiceNow instance or table: summarize active ACLs by decision, operation, and type; flag missing-role or security-attribute ACLs; sample deny rules. Read-only.

Instructions

Access control posture for the instance or one table: active ACLs by decision type (Allow If vs Deny Unless), operation and type, ACLs whose required role does not exist (these deny everyone from Brazil when glide.security.acl_with_invalid_roles_strict_deny is on), ACLs that use security attributes, AI agent / workflow / skill / flow ACL types, and a sample of deny ACLs with links. Read-only

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": "get_acl_posture"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax rows in each list (default 25, max 200)
tableNoLimit to one table (its table and field ACLs). Omit for the whole instance

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the trailing 'Read-only' adds nothing. The description does add genuine behavioral context beyond annotations: it explains that ACLs with missing required roles are surfaced and that their effect depends on glide.security.acl_with_invalid_roles_strict_deny. It omits any note on result size, sampling method for the deny list, or performance cost.

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 scope statement is front-loaded and each listed category carries information, so little is padding. The single run-on enumeration is dense and slightly awkward to parse ('these deny everyone from Brazil'), but it is not verbose fluff.

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 no output schema, the description must convey the return shape, and it does so by enumerating the report sections plus the deny sample with links. For a two-parameter, annotation-covered read tool this is nearly complete; the only gap is how the limit interacts with the multiple lists.

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 100%, so both parameters are already documented in the schema. The description reinforces the table parameter by framing the tool as scoped to 'the instance or one table', but adds no syntax, format, or interaction detail beyond that. Baseline 3 applies when the schema carries the parameter burden.

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 the resource precisely ('Access control posture for the instance or one table') and enumerates exactly what the report contains (ACLs by decision type, invalid-role ACLs, attribute-based ACLs, AI agent/workflow/skill/flow ACL types, deny samples). An agent can tell this is a posture/audit report rather than a single-ACL fetch like get_acl. It stops short of explicitly distinguishing itself from the sibling ACL tools, so a 4 rather than 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?

Usage is only implied: the enumerations of decision types and invalid-role ACLs suggest an auditing/compliance use case, and 'Omit for the whole instance' hints at scope choice. There is no explicit when-to-use versus get_acl or get_agent_access_matrix, and no stated prerequisites or when-not conditions.

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

Deploy Server

Other Tools