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

Annotations declare readOnlyHint=true and destructiveHint=true, which is an unusual combination. The description resolves this tension by explaining the real behavior: it reveals a secret and lifts a lock, so it is read-only in data terms but destructive in access terms. It also adds that the code is shown once and never stored, and that trusted-device approval is required. This goes beyond the annotations and clarifies the risk profile.

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, dense paragraph that front-loads the core action and consequence, then gives the required approval workflow. Every sentence earns its place: the 'exit door' metaphor, the once-and-never-stored warning, and the step-by-step approval instructions are all necessary for correct use. No filler.

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?

The description covers the purpose, the side effect, the security model, and the prerequisite approval flow. An output schema exists, so return values need not be described. The only minor gap is that it doesn't explicitly state what happens if the approval session is missing or expired, but the instructions imply the session must be valid. Overall, this is complete enough for an agent 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?

Schema coverage is 67%: domain and companyId are described, but approvalSessionId is not. The description compensates by explaining exactly what approval_session_id is and how to obtain it, which is the most important parameter for this tool. It also clarifies that domain is the target of the reveal. The description adds meaning beyond the schema, especially for the approval flow.

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 states a specific verb ('Reveals'), a specific resource (the domain's transfer authorization/EPP code), and the critical side effect (lifts the transfer lock). It also frames the tool as 'the customer's exit door,' which clearly distinguishes it from sibling domain tools like formation_get_domain_order or formation_get_domain_transfer_status. An agent can tell exactly what this tool does and why it is special.

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 explicitly explains when to use this tool (to reveal the EPP code and lift the transfer lock) and gives a precise prerequisite workflow: open a trusted-device approval with approval_session_create_approval_session, have the user approve, then pass the session id. It also implies this is not a simple read by warning that the code is shown once and never stored. This is strong usage guidance.

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