audit_ai_agents

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the scope of checks and the Dataverse dependency, but it does not explicitly state whether the audit is read-only, what permissions are needed, or whether any changes are made, leaving some safety-related behavior opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long and front-loaded with the action verb. The first sentence is dense but information-rich, enumerating the specific checks concisely; the second gives a clear use case. No filler or unnecessary words.

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

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

The description covers the tool's check types and intended use, and the schema handles parameter details. However, there is no output schema and the description does not describe what the audit returns or how results are structured, which is a notable gap given the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, and the schema's parameter description already explains the default services and the Dataverse requirement. The tool description reinforces the Dataverse dependency but adds little beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Audit' and clearly identifies the resource as the organisation's AI attack surface using Maester's AIAgent checks (MT.1113–MT.1122). It lists concrete check categories, which distinguishes it from the more general sibling tool run_maester_tests.

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

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

The description explicitly states its intended use: 'Use this to let an AI agent police the org's *other* agents and MCP servers.' It also mentions the Dataverse service requirement. However, it does not explicitly say when not to use it or name alternative tools for general Maester tests.

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