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

With no annotations, the description carries the full burden and does so well. It discloses the scope of results (only the authenticated account's domains), the return content (metadata with verification status), and — most valuably — that the tool is gated on an authenticated session, including the exact auth path and the 'then call this tool again' re-invocation behavior. It doesn't cover error behavior when unauthenticated or pagination, but for a read-only list the key traits are disclosed.

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 structure is front-loaded: purpose first, return content second, and the ACCESS prerequisite last. Each sentence earns its place, including the auth workflow which is genuinely actionable. The ACCESS block is slightly verbose with the inline em-dash clause, but it remains organized and 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?

For a zero-parameter, read-only list with no output schema and no annotations, the description covers everything needed to call it correctly: what it lists, whose domains it lists, what it returns, and the session prerequisite with a resolution path. Minor omissions — no pagination note and no explicit routing to get_domain for single-domain lookups — keep it just short of fully complete.

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 tool has zero parameters, which sets the baseline at 4 — there is nothing for the description to document. The phrase 'for the authenticated account' usefully clarifies the implicit scope of the empty parameter set, so the description adds what little meaning is possible beyond the schema.

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 a specific verb and resource — 'List all domains' — and immediately scopes it ('for the authenticated account') and states the return payload ('domain metadata including verification status'). This clearly distinguishes it from siblings like get_domain (singular lookup), add_domain, and delete_domain without needing to open their schemas.

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 gives explicit context for when the tool is appropriate (enumerate the authenticated account's domains) and states a concrete prerequisite: a Proof account and an authenticated session. It even provides the resolution workflow (authenticate via MCP, or start_login then call again). The only gap is that it never names an alternative tool to use instead, so when-versus-alternatives is only implicitly conveyed by the 'list' verb.

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