manage_information_protection_policies

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the agent knows this tool can perform destructive operations and isn't idempotent. The description adds context about what types of policies are managed (data classification, encryption, rights management) which provides useful domain context. However, it doesn't disclose important behavioral details like authentication requirements, rate limits, or what specific destructive actions might be performed (e.g., policy deletion).

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 a single, efficient sentence that gets straight to the point without unnecessary words. It's appropriately sized for a multi-purpose tool with 6 parameters. However, it could be slightly more structured by explicitly mentioning the CRUD operations supported (list, get, create, update, delete) that are defined in the schema.

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 (6 parameters including nested objects, multiple action types, and destructive operations), the description is somewhat minimal. While annotations cover the safety profile, and the schema documents parameters well, the description doesn't address important contextual aspects like typical use cases, prerequisites, or what the tool returns (no output schema exists). For a tool with destructiveHint=true, more guidance about safe usage would be helpful.

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 100% schema description coverage, the input schema already documents all 6 parameters thoroughly. The description doesn't add any meaningful parameter semantics beyond what's in the schema - it doesn't explain parameter relationships, provide examples, or clarify how the 'action' parameter determines which other parameters are relevant. The baseline score of 3 is appropriate when 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: 'Manage Azure Information Protection policies for data classification, encryption, and rights management.' It specifies the resource (Azure Information Protection policies) and the broad functional areas (data classification, encryption, rights management). However, it doesn't distinguish this tool from sibling tools like 'manage_sensitivity_labels' or 'manage_retention_policies' which might overlap in the information protection domain.

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 provides no guidance on when to use this tool versus alternatives. With many sibling tools in the Microsoft 365/security management space (like manage_sensitivity_labels, manage_retention_policies, manage_defender_policies), there's no indication of how this tool fits into the broader ecosystem or when it should be preferred over other policy management tools.

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