backup_policies

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

Annotations indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and idempotency. The description adds valuable context by specifying the output format (JSON) and supported policy types (e.g., Conditional Access, Intune policies), which goes beyond annotations. It doesn't mention rate limits, authentication needs, or detailed behavioral traits, but with annotations present, the bar is lower, and the description provides useful supplemental information.

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 concise and front-loaded, with two sentences that efficiently convey the core purpose and scope. Every sentence earns its place: the first states the main action and use cases, and the second lists supported policy types without redundancy. No wasted words or unnecessary details.

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?

Given the tool's complexity (4 parameters, 100% schema coverage, annotations provided), the description is reasonably complete. It covers the tool's purpose, output format, and supported policy types. However, without an output schema, it doesn't explain return values (e.g., structure of JSON output), and it lacks details on error handling or limitations. Annotations help, but some gaps remain for a tool with multiple parameters and no 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?

Schema description coverage is 100%, with all parameters well-documented in the schema (e.g., 'action' with enum values, 'policyTypes' with options). The description adds minimal parameter semantics beyond the schema, mentioning 'JSON format' which aligns with the 'outputFormat' parameter but doesn't provide additional details. Baseline 3 is appropriate since the schema does the heavy lifting.

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 clearly states the tool's purpose: 'Export Microsoft 365 policies to JSON format for backup, disaster recovery, and migration.' It specifies the verb (export), resource (Microsoft 365 policies), and format (JSON), and lists supported policy types. However, it doesn't explicitly differentiate from sibling tools like 'manage_conditional_access_policies' or 'manage_intune_windows_policies', which appear to be management-focused rather than export-focused.

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 usage for backup, disaster recovery, and migration scenarios, providing some context. However, it doesn't explicitly state when to use this tool versus alternatives (e.g., 'manage_*' tools for editing policies or 'generate_*_report' tools for reporting). No exclusions or prerequisites are mentioned, leaving usage guidelines somewhat vague.

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