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

Annotations already establish that this is a read-only, idempotent, non-destructive operation, so the description does not need to repeat safety details. It adds useful behavioral context by naming the Microsoft-specific verdict fields and saying each is explained, though it does not describe error behavior or output shape.

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?

Two sentences, both front-loaded and purposeful. The first sentence names the tool's domain, returned fields, and Microsoft scope; the second sentence routes the agent to the correct sibling when appropriate.

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?

With no output schema, the description carries responsibility for explaining what comes back, and it does so by listing the verdict and authentication fields. It is nearly complete for correct invocation, though it does not specify the exact output format beyond saying fields are explained.

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?

The single headers parameter is fully documented in the schema as the full raw headers of a message delivered to a Microsoft mailbox. The description reinforces that the input is Microsoft-specific raw headers but adds no syntax, examples, or format details beyond the schema, so baseline 3 is appropriate.

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?

States a specific verb and resource: reading the spam verdict Microsoft 365 or Outlook stamped on a delivered message. It enumerates the exact verdict and authentication fields returned (SCL, BCL, PCL, SFV, category, SPF/DKIM/DMARC) and explicitly distinguishes itself from analyze_headers.

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?

Gives a direct usage condition: use it when mail lands in Outlook junk. It also names the alternative analyze_headers for Gmail or other providers' routing and alignment, making the routing decision explicit.

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