Where to launch a startup: researched directories, launch platforms, newsletters and press.
Scored across 2 tools
The two tools have clearly distinct purposes: get_site retrieves details for a single domain, while search_sites returns a filtered/sorted list of submission platforms. There is no realistic overlap or risk of misselection.
Both names follow a clean verb_noun pattern: get_site and search_sites. Singular/plural usage is predictable and mirrors the single-item versus list semantics.
Two tools is thin for a directory-style service, though it matches a minimal lookup/search API surface. The set is cohesive but borderline under-scoped.
The core read-only workflows are covered: searching/browsing platforms with optional filters and retrieving a specific site by domain. There are only minor potential gaps, such as richer metadata or pagination, that an agent could likely work around.
Look up one site on Submit.co by its domain: what it costs, the link a product gets, who gets in, how much exposure it gets, and where to submit.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The site's domain, e.g. betalist.com. A URL works too |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description is consistent with them ('look up'). It adds substantive payload context — the five categories of data returned — which is genuinely useful, but says nothing about behavior on an unknown domain, URL normalization, or result size.
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?
A single front-loaded sentence that names the resource and the identifying parameter first, then the returned fields. The colloquial phrasing ('who gets in', 'how much exposure it gets') is compact but slightly less precise than plain terms like 'submission access' or 'traffic'.
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 usefully substitutes by sketching the return contents, and a one-parameter lookup needs little more. Minor gaps remain around failure modes and input normalization, which are not addressed anywhere.
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 domain property already explains the format with an example and notes that a URL works. The description's 'by its domain' restates the schema rather than adding new semantics, 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 — 'look up one site ... by its domain' — and enumerates the attributes returned (cost, link, access, exposure, submission target). The singular 'one site by domain' implicitly separates it from the sibling search_sites, though it never names that sibling.
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?
Usage is only implied: the agent can infer this is for the case where a specific domain is already known. There is no explicit when-to-use, no when-not-to-use, and no pointer to search_sites for discovery-style lookups.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List launch platforms, directories, communities, newsletters, press and review sites that take product submissions, highest Ahrefs Domain Rating first. Every filter is optional; combine them to narrow the list.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Part of the site's name or domain, e.g. hunt or betalist | |
| type | No | Kind of site | |
| limit | No | Sites per page (default 25) | |
| niche | No | Products the site is for. general sites take any product | |
| price | No | free: free to list, including sites with paid options. free_without_backlink: free without having to link back to them. paid: paid only | |
| offset | No | Sites to skip, from next_offset of the previous page | |
| backlink | No | The link the product gets: dofollow helps SEO | |
| exposure | No | featured_to_audience: shown on their homepage, newsletter or social. depends_on_votes: visibility depends on upvotes. listing_only: a listing page, little promotion | |
| acceptance | No | everyone: every product that fits. reviewed: most get in. selective: only a few are picked |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds genuinely new behavioral context beyond them: the result ordering is by Ahrefs Domain Rating descending, which an agent needs to interpret output. It does not disclose result volume or that pagination is offset-based (that lives only in the schema).
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, zero filler, with the scope and ordering front-loaded and the filtering advice second. Every clause earns its place.
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?
Nine parameters, all enums documented, annotations present, no output schema. The definition covers what the list is, how to narrow it, and how it is sorted; only the shape of a returned site record and page-size defaults are left implicit (the latter is in the schema).
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 every enum value is spelled out there, so the schema does the heavy lifting. The description only adds the meta-point that all filters are optional and combinable, which is already implied by required=[]; no filter-specific meaning is added beyond that.
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 (list/search) and an explicit resource taxonomy (launch platforms, directories, communities, newsletters, press, review sites that accept product submissions) and adds ordering semantics (highest Ahrefs Domain Rating first). Against the only sibling, get_site, the list-vs-single-site distinction is immediately clear.
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?
"Every filter is optional; combine them to narrow the list" tells the agent how to use the tool (progressive narrowing from a broad list). It gives no explicit when-not-to-use or pointer to get_site for fetching one site's full details, so it stops 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.
get_sitesearch_sitesA directory of product launch platforms: where your product qualifies and how each form is filled.
Find where to submit your startup. Searches a free list of directories with real submission results.
Search a launch directory of new products, and submit and publish your own listing.
Find live startup/SaaS/AI launch directories, with submit URL and free/badge/queue/paid status.
Add one secure layer between your agents and this server.
