Search Intune policies

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

Annotations already signal readOnly, openWorld, idempotent, and non-destructive behavior. The description adds valuable context beyond annotations by revealing that results come from 'internally generated Microsoft Graph /beta requests', that isAssigned values are 'Graph-reported hints', and that results can be RBAC-filtered. 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 compact, front-loads the core action, and every sentence delivers either a caveat (non-unique display names) or a routing hint (get_policy_assignments). It is slightly dense but remains readable and well-organized. It earns a high score, but not a 5 because it could be tighter by removing the redundant 'Searches supported' phrasing with the title.

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 search-and-return tool, the description explains how to consume results and what caveats apply, and the output schema covers expected return values. It does not explicitly discuss pagination or cursor semantics, but those are parameters documented in the schema, so the description need not repeat them. The presence of an output schema further reduces the burden on the description.

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?

Schema description coverage is 0%, so the description carries the full burden. It explains the key output semantics (id and categoryId) and the critical non-uniqueness caveat. It does not explicitly name limit, cursor, or platform, but given the 0% schema coverage, the description compensates enough for an agent to understand the primary inputs and expected outputs.

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 ('searches') and resource ('supported Intune policy and application categories') and differentiates it from siblings by being the path to get_policy_assignments via id/categoryId. It also calls out the non-uniqueness of display names, which clarifies a subtle edge case.

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?

Explicitly states that returned id and categoryId should be passed as policyId and category to get_policy_assignments, and warns not to silently choose a single record when display names are not unique. It also clarifies that isAssigned values are only hints and get_policy_assignments reconciles them, giving clear, decision-relevant usage context.

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