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

Goes well beyond the annotations: it discloses the state side effect ('A verified domain joins the user's inventory'), which explains the non-readOnly profile, and the error contract ('A failed DNS lookup returns an error, never \'not owned\''), which prevents a serious misinterpretation. It also bounds cost ('Cannot spend money'), a useful boundary given budget-related siblings.

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?

Short, front-loaded with the core mechanism before the action modes and behavioral notes; every sentence carries information. Slight fragmentation ('Cannot spend money.') reads as a clipped addendum rather than integrated prose.

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?

With no output schema, the description does the necessary work by indicating what 'start' returns and how failures surface, and it covers the mutation side effect. What 'check' returns on success is only implied through the inventory statement, and domain input format is unaddressed.

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 50% and the description compensates for the enum parameter by explaining what 'start' returns (a TXT record to publish) and what 'check' does (looks for it), which is more than the schema's bare default note. The 'domain' parameter still has no format guidance (bare domain vs. URL), leaving a small gap.

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?

Names a specific verb and resource ('Proves the user controls a domain') and the mechanism (DNS TXT challenge), which separates it from nearby siblings like audit_domain, list_domains, and check_live. The two action modes are also spelled out, so an agent knows what the tool actually performs.

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?

Gives a concrete trigger condition: 'For when the user says a domain is theirs and the claim matters.' That is a clear context for invocation, but there is no explicit exclusion or named alternative (e.g., when to prefer audit_domain or check_live instead).

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