validate_domain

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

With no annotations, the description carries the full disclosure burden. It declares the DNS checks performed (A record, MX), the negative scope ('not mailbox/SMTP'), and the full return dict including is_disposable and cost_usd. It does not mention network latency or whether the operation is billable, but the cost_usd key at least surfaces cost.

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?

One purpose sentence, a compact Args/Returns block, and no filler. The critical exclusion is front-loaded, and every clause adds value without redundancy.

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 1-parameter, no-output-schema tool, the description covers what it validates, what it ignores, the exact input shape, and every return key. An agent can confidently invoke it and interpret the result without additional context.

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 schema only says 'domain: string' with zero coverage, so the description must compensate. It does so excellently by defining accepted forms ('Hostname or URL'), providing examples ('example.com' or 'https://example.com/path'), and implying URL normalization – exactly the guidance an agent needs.

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 'Validate a domain: format, DNS A record, and MX' – a specific verb and resource plus the exact checks performed. The parenthetical '(not mailbox/SMTP)' proactively disambiguates from email-validation siblings like enrich_email and makes the boundary explicit.

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?

It clearly states the validation scope and explicitly rules out mailbox/SMTP, signaling that this tool is for domain-level checks rather than email deliverability. It doesn't name alternatives like validate_domain_batch, but the single-domain argument and sibling name make that choice inferable.

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