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

With no annotations, the description carries the full burden of behavioral disclosure, and it delivers thoroughly. It explains that the tool runs every plan-granted check, that email/DNS verification level changes thoroughness, that it fails if an audit is already running, and that it returns the audit id, starting status, and queued-check count. It even advises polling via get_audit_status, giving the agent a realistic model of the tool's asynchronous behavior.

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 three short paragraphs but every sentence earns its place: the first states the core purpose, the second details prerequisites and failure modes, and the third covers return values and follow-up polling. It is concise yet information-dense, with the main action front-loaded.

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?

For a one-parameter tool with an output schema already present, the description is complete: it covers the parameter, the behavior, all failure conditions, the return values, and the recommended next step (polling). There is no missing information an agent needs to invoke the tool correctly.

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?

Input schema coverage is 0% and the schema only shows domain_id as an integer, but the description compensates by defining it as 'the id of a domain on your account that is active for checks.' This adds semantic meaning, constraints, and selection criteria far beyond the bare schema. For the single parameter, this is more than adequate.

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 opens with 'Start a new security audit,' which combines a specific verb and resource, leaving no doubt about the tool's function. It clearly distinguishes itself from sibling query tools (get_audit, list_audits) by being the only one that initiates an audit, not just retrieves or lists them.

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 explicit preconditions (domain_id must refer to a domain active for checks) and enumerates all failure situations: domain nonexistence, not being active, no checks granted by the plan, or an audit already running. It also routes the agent to get_audit_status for polling. It stops short of explicitly saying 'use this instead of get_audit/list_audits,' but the usage context is unambiguous.

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