Find lookalike domains of a brand's website: typos, swapped letters, look-alike characters, added words and other TLDs. Shows which of them resolve in DNS and what their front page shows. One read-only tool, no sign-up. Registry name: com.openbait/lookalike-domains. Web version: https://openbait.com/tools/typosquat-check
Scored across 1 tool
Only one tool is exposed, so there is no risk of selecting the wrong tool or confusing overlapping purposes. Its scope is clearly limited to lookalike-domain checking.
The single tool name check_lookalike_domains follows a clear verb_noun snake_case convention and is readable. With only one tool there is no inconsistency to assess.
The server has a narrow, well-defined purpose and one tool directly matches that purpose. A single tool is slightly thin but reasonable for a focused lookalike-domain checker.
The tool covers the core domain-checking workflow: typo variants, character swaps, added words, alternate TLDs, DNS resolution, and front-page classification. Minor follow-up details such as WHOIS or certificate information are not included, but the stated check is largely complete.
Find lookalike domains of a brand's website: typos, swapped letters, look-alike characters, added words and other TLDs. Checks which of them resolve in DNS and what their front page shows (a page using the brand's name, a redirect to the brand's own site, another live site, or nothing). Read-only. Same check as https://openbait.com/tools/typosquat-check.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | the brand's website, e.g. example.com or https://www.example.com |
| Name | Required | Description |
|---|---|---|
| domain | Yes | the registrable domain that was checked |
| summary | Yes | |
| resultUrl | Yes | the same result on openbait.com |
| lookalikes | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the restating of 'Read-only' is redundant rather than additive. What the description does add is genuinely useful behavior: it says the check resolves each candidate in DNS and inspects the front page, and names the possible outcomes (brand-name page, redirect to brand, other live site, nothing). It doesn't mention latency or result volume, which for an open-world network scan would be useful.
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 tight sentences, front-loaded with the core action, then the variant list, then the evaluation behavior. Every clause carries information and there is no 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?
Output schema exists, so return shape needn't be spelled out, yet the description still previews the outcome categories the agent will see. Combined with the read-only framing and the external reference, nothing needed to invoke this correctly is missing.
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?
Only one parameter, and the schema already documents it at 100% coverage with an example ('example.com or https://www.example.com'). The description adds nothing about the domain argument beyond what the schema states, 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 and resource (find lookalike domains of a brand's website) and enumerates exactly what kinds of variants are generated: typos, swapped letters, look-alike characters, added words, other TLDs. An agent knows precisely what this tool produces 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?
The scope is clear — given a brand domain, it enumerates and evaluates lookalikes — and the reference to the equivalent openbait.com tool gives the agent a concrete mental model. There are no sibling tools to route against and no explicit 'do not use for X' exclusion, which keeps it just short of a 5.
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_lookalike_domains
Add one secure layer between your agents and this server.