Search pending delete and recently dropped domain names from Claude, ChatGPT or any MCP app: drop times, Rank, Linking Domains and every filter of the advanced search.
Scored across 2 tools
The two tools are cleanly separated: get_domain resolves exactly one name's full status/drop record, while search_domains queries the filtered list of many names. The descriptions explicitly cross-reference each other ('get_domain looks up one name in any status'), removing any residual overlap.
Both names follow the same verb_noun snake_case pattern (get_domain, search_domains). The singular/plural distinction is semantically motivated (one name vs many), not an inconsistency.
Two tools is thin, though the domain (a read-only pending-delete/domain-status lookup service) genuinely needs only a single-record lookup and a filtered search. No redundant tools, but the surface is at the low end of what feels complete.
Read-only data service, so no CRUD lifecycle is required; single lookup plus rich filtered search with pagination, totals, and CSV links covers the core workflows. Minor gaps like a bulk multi-domain lookup or a metadata/status enumeration tool are workable around.
Look up one domain name on PendingDelete.net's lists: its status (Redemption, Pending Delete, Released — checking, Available, Caught), when it drops (US Eastern) and whether that time is confirmed, length, registrar, registration date, Linking Domains, Rank, which of the same name's .com, .net and .org are registered, and its page. The lists hold names in redemption, in pending delete or released in the last 90 days; for any other name it says so and gives the page where a person can run a live registry lookup.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | A domain name, e.g. example.com. |
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| rank | No | |
| drops | No | |
| domain | Yes | |
| length | No | |
| status | No | |
| tracked | Yes | |
| on_lists | Yes | |
| released | No | |
| registrar | No | |
| registered | No | |
| figures_from | No | |
| status_means | No | |
| drops_eastern | No | |
| linking_domains | No | |
| released_eastern | No | |
| drop_time_confirmed | No | |
| adjoining_registered | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the description is free to add operational detail — and it does: the underlying data source, the 90-day coverage window, the timezone of drop times, whether the drop time is confirmed, and the fallback behavior for out-of-scope names. That fallback is the key behavioral fact an agent needs, since a miss is a normal outcome rather than an error.
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 core action and scoped coverage immediately after. The long field enumeration is dense but each item is a distinct return value the agent may need, and there is no filler. Slightly heavy as a single clause chain, but nothing extraneous.
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?
An output schema exists, so return values need not be spelled out, and yet the description still summarizes the notable fields plus the confirmation flag and timezone caveats. Combined with the explicit coverage limits and miss behavior, an agent has everything required to call it and interpret a negative result.
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?
With one parameter at 100% schema coverage, the schema already documents the "domain" field and its example, so the baseline is 3. The description conveys that the name is matched against the PendingDelete.net lists rather than queried live, which adds a little meaning about how the value is interpreted, but gives no additional format or normalization guidance.
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 a specific verb+resource ("Look up one domain name on PendingDelete.net's lists") and enumerates exactly what is returned: status, drop time, confirmation flag, length, registrar, registration date, Linking Domains, Rank, .com/.net/.org registration state, and page. "One domain name" implicitly contrasts with the sibling search_domains, so an agent can pick between single lookup and search without opening a 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?
It clearly bounds applicability: the lists only cover names in redemption, pending delete, or released in the last 90 days, and for anything else the tool says so and points to a page for a live registry lookup. That tells the agent when results will be meaningful and what a miss means. It stops short of naming search_domains as the alternative for broader queries, so no explicit sibling routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the domain names PendingDelete.net follows: in pending delete (the default) — the last five days before a registry deletes a name and anyone can register it — or, with status, the names released in the last 90 days: available (nobody has registered them again: anyone can register them now), caught (registered again since), or released (still being checked). The same filters as the site's advanced search: a keyword (contains, starts with, ends with, exact, doesn't contain) or a regular expression, words to leave out, a letter pattern, length, hyphens, numbers, IDN, extensions, adjoining .com/.net/.org registered, the drop or release date, confirmed drop times only, registrar, the year first registered, Linking Domains, Rank, real words, people's names and syllables. Each name comes with its drop (or release) date and time (US Eastern), length, registrar, registration date, Linking Domains and Rank (Common Crawl's web graph — not Moz DA or Ahrefs DR), which of the same name's .com, .net and .org are registered, and its page on PendingDelete.net. One answer holds 100 names unless limit says otherwise (up to 100), and the total; page gives the next ones, and each answer links the whole list on the site with its CSV. get_domain looks up one name in any status.
| Name | Required | Description | Default |
|---|---|---|---|
| idn | No | Include internationalised names (xn--). Default true. | |
| page | No | Which page of the results, from 1. Pages reach the first 10,000 names. | |
| sort | No | Order of the names. Default drop_date: the nearest drop first (for the released statuses, the newest release first). | drop_date |
| limit | No | Names in this answer, 1–100 (more than 100 gives 100). Default 100. | |
| match | No | How keyword matches the name before the dot. Default contains. | contains |
| order | No | asc or desc, as the words say (desc: the most Linking Domains, the highest Rank, the newest registration first). Default: nearest drop, A to Z, shortest, most Linking Domains, highest Rank, oldest registration, most adjoining registered. | |
| regex | No | A regular expression over the name before the dot, used instead of keyword (MySQL REGEXP; letters, digits, - ^ $ . * + ? ( ) [ ] { } | \ and commas; no back-references). E.g. ^[a-z]{4}$ for four letters. | |
| status | No | Which names: pending_delete (the default: they drop within five days), available (released in the last 90 days and not registered again: anyone can register them now), caught (released in the last 90 days and registered again since), or released (released, still being checked). One at a time. | pending_delete |
| exclude | No | Leave out names containing any of these (up to 5), e.g. ["shop", "247"]. | |
| hyphens | No | Include names with hyphens. Default true. | |
| keyword | No | Text to find in the name before the dot: letters, digits and hyphens, e.g. "shop". How it matches is set by match. | |
| numbers | No | Include names with digits. Default true. | |
| min_rank | No | A Rank of at least this (0–10 score of where the name stands in Common Crawl's web graph; see the answers for exactly how it is worked out). | |
| surnames | No | Only last names: alone, after a first name, or first with a trade's words after it (smithlaw). | |
| syllables | No | Exactly this many syllables (real words only). | |
| extensions | No | Extensions to search, without the dot, e.g. ["com"] or ["com", "net", "org"]. Leave out for every extension PendingDelete.net tracks; most people want ["com"]. | |
| max_length | No | Most characters before the dot (25 means 25 or more). | |
| mens_names | No | Only names starting with a man's first name (alone, or with a last name and more after it). | |
| min_length | No | Fewest characters before the dot. | |
| real_words | No | Only names made of everyday English words — not people's names or places. | |
| registrars | No | The registrar the name was with, as the registry writes it (up to 10); the commonest in pending delete now: GoDaddy.com, LLC; NameCheap, Inc.; GMO Internet Group, Inc. d/b/a Onamae.com; Spaceship, Inc.; Gname.com Pte. Ltd.; Dynadot Inc. | |
| drop_date_to | No | Drops or was released on or before this day: YYYY-MM-DD, or yesterday, today or tomorrow (US Eastern). The same day in both for one day. | |
| womens_names | No | Only names starting with a woman's first name. | |
| drop_date_from | No | Drops (pending delete) or was released (the other statuses) on or after this day: YYYY-MM-DD, or yesterday, today or tomorrow (US Eastern). | |
| letter_pattern | No | The shape of the name before the dot: C a consonant, V a vowel, L any letter, N a digit; lowercase letters, digits and hyphens stand for themselves. E.g. CVCV (like "bobo"), LLLN, go-L. | |
| registered_to_year | No | First registered in this year or earlier, e.g. 2005 for names older than about twenty years. | |
| min_linking_domains | No | At least this many other domains linking to the name in Common Crawl's web graph (the site's steps: 1, 10, 100, 1000). | |
| adjoining_registered | No | Adjoining TLDs registered: keep names whose same name is registered right now in each of these, e.g. extensions ["com"] with ["net", "org"] gives the .com names whose .net and .org are both registered (someone owns them: a sign the name is wanted). From the zone files, once a day; .com, .net and .org names only. | |
| registered_from_year | No | First registered in this year or later. | |
| confirmed_drop_times_only | No | Only names whose drop time is worked out from the registry's own record of when the name entered pending delete, not estimated. |
| Name | Required | Description |
|---|---|---|
| to | Yes | |
| from | Yes | |
| more | Yes | |
| page | Yes | |
| sort | Yes | |
| limit | Yes | |
| names | Yes | |
| order | Yes | |
| total | Yes | Names that match; null when more than 10,000 and not counted |
| status | Yes | |
| search_url | Yes | |
| total_text | Yes | |
| download_max | Yes | |
| download_url | Yes | |
| figures_from | Yes | |
| released_days | Yes | For the released statuses: how many days back they reach |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a read-only, idempotent, non-destructive search. The description adds substantial behavioral context beyond those annotations: it explains what each status means, that results are capped at 100 per answer with a total and page cursor, that each answer links the full list with a CSV, and that dates are US Eastern. It also clarifies that Rank is Common Crawl's web graph, not Moz DA or Ahrefs DR.
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?
The description is front-loaded with the core purpose and status options, and every sentence carries information. However, it is a dense single paragraph that repeats some schema-level details about filters and return fields, making it longer than strictly necessary. It is efficient but not maximally concise.
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?
Despite the tool's complexity (30 parameters), the description covers the essential context an agent needs: status semantics, default behavior, result size and pagination, output fields, and sibling-tool routing. An output schema exists, so the description does not need to explain return values, but the extra behavioral details make it fully complete.
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 the schema already documents all 30 parameters in detail. The description provides a high-level summary of filter categories and repeats the status semantics, but it does not add meaningfully more per-parameter guidance than the schema. Baseline 3 is appropriate when the schema does the heavy lifting.
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 a specific verb and resource: searching the domain names PendingDelete.net follows. It also distinguishes the tool from its sibling by ending with 'get_domain looks up one name in any status.' An agent can immediately tell what this tool does and how it differs from get_domain.
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 description explicitly defines the default status (pending_delete) and the meaning of each alternative status (available, caught, released). It also provides a clear routing rule at the end: use get_domain for a single name in any status. This is explicit when-to-use guidance with a named alternative.
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.
search_domains1 field changedInput schema / properties / registrars / descriptionPrevious value: -"The registrar the name was with, as the registry writes it (up to 10); the commonest in pending delete now: GoDaddy.com, LLC; NameCheap, Inc.; GMO Internet Group, Inc. d/b/a Onamae.com; Gname.com Pte. Ltd.; Spaceship, Inc.; Dynadot Inc."New value: +"The registrar the name was with, as the registry writes it (up to 10); the commonest in pending delete now: GoDaddy.com, LLC; NameCheap, Inc.; GMO Internet Group, Inc. d/b/a Onamae.com; Spaceship, Inc.; Gname.com Pte. Ltd.; Dynadot Inc."search_domains1 field changedInput schema / properties / registrars / descriptionPrevious value: -"The registrar the name was with, as the registry writes it (up to 10); the commonest in pending delete now: GoDaddy.com, LLC; NameCheap, Inc.; GMO Internet Group, Inc. d/b/a Onamae.com; Spaceship, Inc.; Gname.com Pte. Ltd.; Dynadot Inc."New value: +"The registrar the name was with, as the registry writes it (up to 10); the commonest in pending delete now: GoDaddy.com, LLC; NameCheap, Inc.; GMO Internet Group, Inc. d/b/a Onamae.com; Gname.com Pte. Ltd.; Spaceship, Inc.; Dynadot Inc."get_domainsearch_domainsBulk domain checking for AI chats: availability, aftermarket prices, archive.org history, buy links
Search 55M+ expired domains, auctions, marketplaces & drops with SEO metrics, spam score and filters
Screen expired domains: availability, drop stage, history, brandability, trademark risk.
Domain search MCP: .com names verified available live via Verisign RDAP - not AI guess lists
Add one secure layer between your agents and this server.
