iam_natural_language_query

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

Annotations already establish read-only, open-world, idempotent behavior. The description adds that the tool always returns a summary plus understandable details, which helps an agent know what to expect in the response. Nothing contradicts the annotations.

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?

Two short sentences carry the essential behavior and response expectation with no filler. The key action is placed first and the response behavior second, making it easy to scan.

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?

For a read-only NL query tool with no output schema, the description gives a basic response shape (summary + details) and input tolerance. It lacks sibling usage guidance and parameter detail, so an agent still has uncertainty about when to choose this over neighboring query tools and what limit controls. Overall it is adequate but not complete.

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 schema has two parameters but 0% description coverage, so the description needed to explain them; it does not mention question or limit at all. The question parameter is inferable from the tool's purpose, but limit semantics are left entirely to the schema title and default. This is a meaningful gap because limit's behavior is not self-evident in an NL-query tool.

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 identifies a clear action—interpret an IAM natural-language question—and adds the key differentiator that answers correlate Entra with Azure. It is not a bare tautology because it specifies the resource scope and output orientation. However, it does not explicitly contrast with timeline/agent/pim variants.

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 implies the tool is for open-ended IAM questions phrased naturally, noting that exact wording is not required. It provides no explicit when-to-use guidance or exclusions relative to sibling natural-language tools such as timeline_natural_language_query or pim_natural_language_query. The context is sufficient to infer general use but not to make a confident selection among siblings.

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