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

The annotations already establish readOnlyHint=true and openWorldHint=true, so the description's job is added context — and it does supply real value: a 6-hour cache window, a $0.010 per-call price, and the x402 payment rail (USDC on Base or Solana). What it omits is failure behaviour: what happens for an unresolvable or parked domain, which fields are nullable when schema.org markup is missing, and whether a cached response still bills the same. Those gaps matter for an open-world paid lookup.

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?

Two sentences, front-loaded with the resource and its outputs, followed by the commercial and payment terms. The only waste is the first clause, which restates the title verbatim before the more informative 'Enriches a company or project domain in one call'. The field list is dense but each item earns its place because no output schema exists.

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 tool with no output schema, describing the return payload is essential, and this description does it thoroughly, covering enrichment sources (schema.org, MX, RDAP) as well as fields. It also surfaces pricing and caching, which the annotations do not carry. Missing only edge-case behaviour on empty or unenrichable domains, which prevents a 5.

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%, with both 'domain' (format and example stripe.com) and 'tx' (alternative to the X-Payment-Tx header) documented in the schema itself. The description reinforces that the input is a bare domain, not a URL, via the phrase 'from a domain', but adds no constraints, normalisation rules, or examples beyond what the schema already states. 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?

The description names a specific verb and resource ('Enriches a company or project domain in one call') and enumerates exactly which fields come back: name/description, logo, socials, emails/phones, address, founding date, technologies, MX provider, RDAP age. That field-level enumeration is what distinguishes it from near neighbours like 'domain' or 'email_check'. It stops short of explicitly naming which sibling to prefer, which keeps it at 4 rather than 5.

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 offers use cases ('For lead research, due diligence and KYB'), which implies when the tool is appropriate. But there is no guidance on when NOT to use it, no mention of the sibling 'domain' tool or of cheap alternatives if only one field is needed. With a paid per-call tool, an explicit 'use this only when you need multiple fields at once' rule would be valuable and is absent.

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