Find domains and domain hacks with live availability, registrar prices, and keyword search demand.
Scored across 3 tools
find_domains is clearly for brainstorming, while check_availability and search_domain both check availability. Their boundary is mostly clear: check_availability handles bulk lists of full domains without quotes, and search_domain handles per-name/TLD quote lookups, but an agent could still hesitate between them.
All three names use consistent snake_case verb_noun structure: check_availability, find_domains, search_domain. The singular/plural difference is minor and does not break predictability.
Three tools are well-scoped for domain discovery: brainstorm names, bulk-check availability, and search per-name quotes. Each tool has a distinct role and none feels redundant.
The surface covers brainstorming, availability checks, and quote lookup across TLDs, which fits the domain-finding purpose. It lacks direct registration actions or TLD enumeration, but those are minor gaps and the registrar link provides a workaround.
Check availability for a specific list of full domains (e.g. ['acme.com','acme.ai']). Returns availability, renewal details where supplied, and a registrar link. This fast lookup does not supply a registration quote; use search_domain for prices. Up to 25 domains per call.
| Name | Required | Description | Default |
|---|---|---|---|
| domains | Yes | Full domain names to check, each including its extension (e.g. ['getacme.com','acme.ai']). Up to 25 at a time. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds real context beyond them: what comes back (availability, renewal details where supplied, registrar link), what is conspicuously absent (no registration quote), and a batching cap of 25.
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?
Three tight sentences, front-loaded with the action, followed by the return-value summary, then the routing note and limit. No filler or repetition.
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 carries the return-value burden and does so (availability, renewal details, registrar link). Combined with the batch limit and sibling routing, an agent has everything needed to call it correctly.
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 100% and the single parameter is fully described there, including the 'including its extension' requirement and the 25-item limit. The description's example format largely restates the schema, so the baseline 3 applies.
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 ('Check availability for a specific list of full domains') with a concrete example, and separates itself from the sibling search_domain by scope (bulk lookup of known names vs. price quoting). An agent can identify it without opening the schema.
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?
Explicitly says when NOT to use it ('does not supply a registration quote; use search_domain for prices') and gives an operational constraint (up to 25 domains per call). It does not mention the other sibling find_domains at all, so routing guidance is good but not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Brainstorm domain names for an idea, product, or company. Returns brandable names and any domain hacks supplied by the source, with availability and monthly keyword search-volume where available. Cached ideas receive a new availability check, and a name it confirms as an ordinary registration (not premium) is priced at its extension's current standard rate. Unknown availability and missing registration quotes are null, never reused from an old search. Use search_domain for a fresh per-name quote or follow the registrar link. A new idea can take about a minute to generate: if the result has status 'generating', call find_domains again with the same arguments after retry_after_seconds, and that call returns the names.
| Name | Required | Description | Default |
|---|---|---|---|
| idea | Yes | The company name, product, or idea to generate domain names for. Example: 'an AI tool that writes SQL'. | |
| tlds | No | Optional. Restrict results to these TLD extensions without the dot (e.g. ['com','ai','io']). Omit to let the finder pick the best-fitting extensions, including domain hacks. | |
| purpose | No | Optional. What the domain is for (e.g. 'startup', 'blog', 'portfolio', 'saas'), to steer the style. | |
| description | No | Optional. A longer description of the business, for more relevant names and better-fitting extensions. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnly/openWorld/non-idempotent/non-destructive), it discloses non-obvious behavior: cached ideas get re-checked availability, unknown availability and missing quotes are returned as null and never reused from stale searches, premium vs standard pricing rules, and an approximate one-minute generation latency with a retry_after_seconds loop. That is substantial context the annotations cannot convey.
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?
Purpose and return content are front-loaded, and every clause carries real information (null semantics, pricing, retry). The caching/pricing sentences are dense and slightly overpacked, but nothing is redundant filler.
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?
There is no output schema, so the description carries return-value duty and does so reasonably: names, availability, search volume, null placeholders, and the 'generating' status with retry_after_seconds. It leaves the exact response shape partially implied, and does not touch the other sibling, but an agent has enough to call and re-call correctly.
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 all four parameters (idea, tlds, purpose, description) are already documented in the schema, including the omit-to-auto-pick behavior for tlds. The description adds only incidental semantics (output includes domain hacks and search volume) and no parameter-level detail beyond the schema, so the baseline 3 applies.
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 first sentence states a specific verb ('Brainstorm') plus resource ('domain names') and the input subject ('an idea, product, or company'). The second sentence sharpens scope by naming the output ('brandable names and any domain hacks'), which plainly separates it from a per-name availability lookup.
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 routes the agent to the sibling search_domain for a fresh per-name quote, which is explicit alternative selection, and it gives concrete retry instructions for the 'generating' status. It never addresses check_availability or states a when-not-to-use condition, so it stops short of full coverage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Request availability and current quotes for a specific name across supported TLD extensions at once. Give a bare label ('acme') to see acme.com, acme.io, acme.ai... or a full domain ('acme.io') to check that one. Availability, registration prices, and renewal details are returned when supplied, alongside a registrar link. Missing fields stay unconfirmed; confirm final terms at the registrar.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The name to check. A bare label ('acme') is expanded across many TLDs; a full domain ('acme.io') checks that exact domain. | |
| tlds | No | Optional. Limit to these TLD extensions without the dot (e.g. ['com','co','io']). | |
| exact_extension | No | Optional. If the name already includes an extension, set true to check only that exact domain instead of expanding across TLDs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, non-destructive, and non-idempotent, so the safety profile is covered. The description adds real value beyond them: it enumerates returned fields (availability, registration price, renewal details, registrar link) and warns that missing fields stay unconfirmed and that terms must be verified at the registrar, which explains the non-idempotent hint (prices fluctuate).
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?
Three sentences, front-loaded with the core action and the two input modes, then the return contents, then the caveat. Every sentence carries distinct information with no 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?
With no output schema, the description carries the burden of describing returns, and it does so explicitly (availability, prices, renewal, registrar link). It also covers input modes, caveats, and the unconfirmed-field behavior, leaving nothing material for an agent to infer before calling.
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%, and the description's explanation of bare-label vs full-domain input and TLD limiting closely mirrors what the schema already documents. It reinforces rather than extends the parameter docs, so the baseline 3 applies.
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 states a specific verb and resource ('request availability and current quotes for a specific name across supported TLD extensions at once') and explains the two input modes, so the agent knows exactly what the tool does. It does not, however, differentiate itself from the siblings check_availability or find_domains, which an agent might confuse with a multi-TLD availability lookup.
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 gives clear usage context: pass a bare label to expand across TLDs, or a full domain to check one, with the tlds parameter as a narrowing option. It stops short of naming alternatives or stating when NOT to use this tool versus check_availability/find_domains.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_availabilityfind_domainssearch_domainLive domain availability, TLD alternatives, dated registrar prices and expert TLD advice.
Domain availability and prices from 40+ registrars, name checks, DNS setup, and a domain broker
Live domain availability and prices across registrars, ranked by true two-year cost.
Compare domain registration and renewal prices across registrars and check exact-name availability.
Add one secure layer between your agents and this server.