Skip to main content
Glama

list_ai_policies

Read-onlyIdempotent

List AI guardrails and policies: sensitive-topic filters and their groups, Guardian providers, custom transformers, and guardrail properties. Filter by active status and cap rows per source.

Instructions

List the guardrails that apply to Otto: sensitive-topic filters and their groups and attachments (sys_gen_ai_filter, sys_gen_ai_filter_group, sys_gen_ai_filter_config), Guardian providers and custom transformers, and guardrail properties. AI Control Tower policy tables are included when the installed version has them (none exist on sn_ai_governance 5.0.6).

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": "list_ai_policies"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax rows per source (default 100)
active_onlyNoOnly active filters (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already establish this as a read-only, idempotent, non-destructive operation, so the bar is lower; the description nonetheless adds real context by disclosing that results are aggregated from several distinct sources and that available sources vary with the installed version (none on sn_ai_governance 5.0.6). It does not discuss ordering, aggregation shape, or how partial results behave if one source is unavailable.

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?

A single dense sentence that front-loads the verb and the resource, then enumerates the sources. The parenthetical table names are informative rather than filler, though the sentence is long and could be split for readability.

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 carries the burden of conveying what comes back, and the enumeration of source categories effectively does that, plus it flags version-dependent emptiness. Missing are details on result shape across the multiple sources and any pagination or ordering behavior for the per-source limit.

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 100%, so both parameters (limit, active_only) are already fully documented in the schema, including the important 'per source' semantics of limit. The description adds no additional meaning about filtering behavior or the interaction between active_only and the multiple source tables, so the baseline 3 applies.

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 gives a specific verb+resource ('List the guardrails that apply to Otto') and then enumerates exactly what is covered: sensitive-topic filters, filter groups/attachments with their table names, Guardian providers, custom transformers, guardrail properties, and version-dependent AI Control Tower policy tables. It does not explicitly distinguish itself from sibling listers such as list_compliance_policies or list_ui_policies, so it falls short of 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 by the scoping phrase 'guardrails that apply to Otto' and the version caveat about sn_ai_governance 5.0.6. There is no statement of when to choose this tool over the compliance or UI policy listers, and no exclusions or prerequisites are given.

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