List unassigned Intune policies

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

Annotations already declare readOnly and idempotent, but the description adds meaningful behavioral context: results include 'an opaque continuation cursor' (pagination mechanism), 'graphUsage describes only the current tool call', and 'resultCount is the number of records on this page.' This clarifies pagination semantics and avoids misinterpretation of counts. It also discloses the specific field set returned. No contradiction with 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?

The description is three sentences long, each earning its place: the first defines the tool's scope, the second gives a specific parameter instruction, and the third describes output contents and pagination semantics. The main purpose is front-loaded, and there is no redundant or filler content. It is efficiently structured and 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?

The description is sufficient for a read-only list tool with an output schema that already defines the return structure. It covers pagination (cursor, per-page count) and key output fields. Minor gaps remain: it does not explain the 'platform' parameter or explicitly state how to request the next page (though the cursor implies it), and the meaning of 'supported' is not elaborated. Overall, the description is highly complete but slightly missing on parameter guidance.

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?

With 0% schema description coverage, the description carries the full burden of parameter explanation. It partially compensates by explaining the 'category' parameter ('set category to application') and implying the cursor's purpose ('opaque continuation cursor'), but it leaves 'limit' and 'platform' completely unexplained. The agent can infer limit from context, but the description does not explicitly state its meaning or range, so the parameter semantics are only partially addressed.

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 states a specific verb ('Lists') and a precise resource: 'supported Intune policies and applications whose assignment collection is empty.' This clearly distinguishes the tool from siblings by focusing on unassigned items, and the additional instruction 'For unassigned apps, set category to application' reinforces the special case. It is unambiguous and differentiates the tool's purpose without needing to open the schema.

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 indicates when to use the tool: when you need policies/applications with empty assignment collections. It also provides a conditional guideline ('For unassigned apps, set category to application'), which helps the agent select the right category value. However, it does not explicitly name alternative tools like search_policies or list_all_device_assignments, nor does it state when NOT to use this tool, leaving some exclusion guidance implicit.

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