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

Annotations already establish that this is a non-read-only, non-destructive, closed-world operation. The description adds materially beyond that: a 25-credit charge, a 2-5 minute reporting window, and a 60-minute test expiry. Costs and timing are exactly the behavioral context annotations cannot convey.

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?

Purpose is front-loaded and every sentence carries information (procedure, polling cadence, timing, cost). The middle sentence is long and run-on, packing three separate instructions together, so structure is efficient but not maximally scannable.

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?

An output schema exists, so return values need not be spelled out, and the description still covers the full usage loop, expected latency, expiry, and credit cost. Nothing an agent needs to invoke this correctly is missing.

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 zero declared parameters, the baseline is 4. The description goes further by naming the operative inputs (seedEmails, testId) and their intended usage, though these names do not appear in the empty schema, which creates a mild mismatch rather than a clarifying one.

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 ('Start an inbox placement test for a mailbox you send from') and immediately contrasts with the sibling 'deliverability_get_test', which it positions as the polling counterpart. An agent can distinguish the two without opening either schema.

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?

Explicitly prescribes the workflow: send one email from the mailbox under test to every address in seedEmails with testId in the body, then poll deliverability_get_test about once per minute. It names the alternative tool and the exact trigger for using it, leaving nothing to inference.

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