Why is my email not arriving?

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

Annotations already declare readOnly and idempotent, and the description adds what results are returned (authentication, reputation, actions) without contradicting the safety hints. It does not mention any side effects or state changes, which aligns with the readOnly 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 two sentences, direct, and includes all necessary details without redundancy. Every phrase contributes to understanding the tool's purpose and behavior, making it highly efficient.

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 there is no output schema, the description adequately sets expectations by listing the types of findings (authentication, reputation, actions) and including guidance on endpoints. It is sufficient for an agent to decide and invoke the tool, though a bit more detail on the exact response format could be added.

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 only parameter, 'domain', is fully described in the schema as restricting the diagnosis. The description adds context by using 'account' but then referencing domains, and the optional nature is clear. This goes beyond the basic schema definition.

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 diagnoses deliverability, listing specific aspects (authentication, reputation, recommended actions) and directly answers the user's question 'why are my emails from example.com landing badly?'. It distinguishes from siblings by focusing on the full diagnostic, not just bounces or DNS requirements.

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?

It explicitly says 'Answers... in one call' and mentions each recommended action has the endpoint that performs it, implying when to use this vs. other tools. However, it does not explicitly state when not to use it (e.g., for isolated bounce lists), so it is clear but not fully exhaustive.

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