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

The description discloses behavioral details beyond the annotations: it returns a testId and seed addresses, may require a header, and requires specific permissions. It also implies an asynchronous workflow by telling the user to poll for results. While not exhaustive, it adds meaningful context about what the tool does and what is needed to use it.

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, front-loaded with the primary action, and packs essential information about return values, follow-up steps, and prerequisites without any fluff. Every sentence earns its place.

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 appropriately explains the return values (testId, seeds, header) and the necessary follow-up (polling). It also covers prerequisites. It does not mention potential errors or what to do if the provider doesn't require a header, but it is sufficiently complete for a simple tool with one optional parameter.

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 has 100% coverage for the single optional 'subject' parameter, with a clear description in the schema. The description does not add any additional parameter semantics, but the schema already fully documents the parameter, so the baseline of 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?

The description clearly states the tool's function: 'Start a seed-list inbox-placement test.' It uses a specific verb ('start') with a specific resource ('inbox-placement test'), and the description of return values (testId, seed addresses, optional header) distinguishes it from sibling tools like get_inbox_placement_test or list_inbox_placement_tests.

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 clear usage context: it explains that after starting a test, you should send to the seeds and then poll get_inbox_placement_test for the verdict. It also states prerequisites (inbox-placement connected, owner/admin key with write/full scope). It does not explicitly name alternative tools, but the workflow is clear enough.

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