manage_exchange_policies

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

The description doesn't add meaningful behavioral context beyond what annotations already provide. Annotations clearly indicate this is a destructive, non-idempotent, write-capable tool (destructiveHint: true, readOnlyHint: false, idempotentHint: false). The description doesn't elaborate on what 'destructive' means in this context (e.g., whether deletions are permanent), doesn't mention authentication requirements, rate limits, or error conditions. No contradiction with annotations exists.

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 immediately communicates the core purpose. Every word earns its place - 'manage' establishes the action, 'Exchange Online policies' specifies the resource, and the three examples provide helpful context without unnecessary elaboration.

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 (8 parameters, destructive operations, no output schema), the description is minimally adequate but has significant gaps. While concise, it doesn't help an agent understand the relationship between this tool and sibling policy management tools, doesn't explain behavioral implications of the destructive annotation, and provides no guidance on parameter usage patterns. For such a complex tool, more contextual information would be beneficial.

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 8 parameters thoroughly. The description mentions policy types (mail flow rules, mobile device access, organization-wide settings) which loosely map to the 'policyType' enum values, but doesn't add significant semantic context beyond what's in the schema. 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 with a specific verb ('manage') and resource ('Exchange Online policies'), and provides concrete examples of policy types (mail flow rules, mobile device access, organization-wide settings). However, it doesn't explicitly differentiate this tool from sibling tools like 'manage_exchange_settings' or 'manage_retention_policies', which might handle overlapping functionality.

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. There are multiple sibling tools that might handle related policies (e.g., 'manage_retention_policies', 'manage_dlp_policies', 'manage_conditional_access_policies'), but the description offers no comparison or context about when this specific Exchange policy tool is appropriate versus those others.

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