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

Annotations declare it is a non-read-only, non-destructive mutation; the description adds meaningful context beyond that — it clarifies a persistent verification record is created and that instructions are handed back to the customer to complete externally. The auth requirement is disclosed explicitly, which is exactly the kind of operational context annotations cannot carry. It stops short of saying whether re-calling creates a duplicate record or how a pending record is cleaned up (delete_domain_verification exists).

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 core action and its output are front-loaded in one sentence, and the access note is clearly separated. The auth block is slightly verbose (parenthetical UI path) but is operationally necessary, so little is wasted.

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 3-param mutation with an output schema, the description covers purpose, side effect, and the credential prerequisite. The remaining gap is the follow-up lifecycle (which sibling checks status and what to do if instructions expire), so it is strong but not fully self-sufficient.

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 description coverage is 100%, so the schema already explains domain, customer_id, and the manual_dns/http_file enum. The description only echoes the method choice as 'DNS/HTTP instructions' and does not add defaults, format rules, or what happens if customer_id is omitted. Baseline 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?

States a specific verb+resource ('Start a B2B domain verification') and names the concrete side effect and output ('Creates a verification record and returns DNS/HTTP instructions'). The 'B2B' qualifier implicitly separates it from start_user_domain_verification, but that sibling is never named, so the distinction still requires the agent to guess.

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?

Provides a real exclusion ('start_login does NOT open this tool') and a precondition (needs a Proof account, authenticate then retry), which is useful routing. However it gives no positive guidance on when to pick this over verify_domain, add_domain, create_verification, or start_user_domain_verification — the most likely selection confusion for this tool.

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