get_mailbox_health

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It is transparent about what the tool returns (mailbox email, warmup ramp, cap, used, remaining, pause, bounce rate), the reset time (UTC midnight), the scope (email sends only), and the edge case of a no-mailbox state. It also clarifies the bounce rate is a 'threaded-only lower bound', which is a useful nuance. It doesn't explicitly state read-only, but the 'get' nature implies it, and no side effects are mentioned.

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, well-structured paragraph that front-loads the primary purpose and then enumerates the return fields. It is concise but information-dense, covering all necessary details without redundancy. Every sentence adds value, and the length is appropriate for the complexity of the tool.

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?

Since there is no output schema, the description must explain the return values, and it does so thoroughly: mailbox email, warmup ramp or fixed cap override, today's cap/used/remaining, pause status, and 30-day bounce rate, plus the no-mailbox state. It also provides relevant context like reset timing and the separate quota distinction, making it fully self-sufficient for an agent to understand expected outputs and behavior.

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 input schema fully documents the single parameter projectId with a clear description ('Project name or ID'). Since schema description coverage is 100%, the baseline is 3. The tool description does not add any additional meaning to the parameter itself, but it doesn't need to because the schema covers it; the description focuses on the return value context instead.

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 retrieves mailbox health state, listing specific data points like warmup ramp, daily cap, used/remaining, bounce rate. It uses a specific verb 'get' with a well-defined resource 'mailbox health', and it implicitly distinguishes itself from sibling tools like get_gmail_status and get_lever_state by focusing on per-mailbox sending limits.

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 context on when to use the tool by explaining it covers the mailbox used for sending, and explicitly notes the daily cap is separate from the plan/billing outreach quota, which helps avoid confusion with other quota-related tools. However, it doesn't explicitly name alternative tools or state dedicated 'when to use' versus 'when not to use' guidance.

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