Skip to main content
Glama

Atom.com — Premium Domains

by com.atom

purchase_domain

Destructive

Purchase an ALREADY-LISTED Atom marketplace domain. This SPENDS REAL MONEY and requires the 'domains:register' scope. Use this ONLY when check_domain_availability reported status 'premium' or 'taken' (a curated Atom listing) for this exact domain, or get_domain_details confirmed it's a listing. If the domain is instead fresh/never-listed (status 'available'), use register_domain instead — never this tool; it will reject a fresh domain with error 'not_a_marketplace_listing'.

MANDATORY two-step flow — never skip the quote:

  1. Call with confirm=false (default) to get a QUOTE: returns the authoritative price, its breakdown (sale_price, registration_fee, vat_amount), the user's current balance, sufficient_funds, whether a saved card exists (has_saved_card / saved_card), and expires_at.

  2. SHOW THE USER: the exact price breakdown, and state plainly which payment method you are about to use and how much it will charge — e.g. "$1,250.00 (listing price $1,200 + $50 registration fee) from your Atom balance" or "...from your saved Visa ending 4242". Get explicit confirmation before proceeding.

  3. Call again with confirm=true, the SAME idempotency_key, and payment_method set to exactly 'balance' or 'saved_card' (REQUIRED at this step — never omit it or guess): commits the charge and the purchase. Returns status='purchased', amount_charged, payment_method, order_id, and order_url.

Rules: never assume or pass a price. Reuse one client-generated idempotency_key across both calls (and any retry) to prevent double-charging. If payment_method='balance' and funds are insufficient, error 'insufficient_funds' reports required/available/top_up_url and whether a saved card exists as an alternative — tell the user both options plainly, do not silently retry with the other method. If payment_method='saved_card' and the charge fails, error 'card_payment_failed' reports why (including if it needs 3D Secure authentication, which cannot be completed here — offer balance or a different card instead). If it reports error 'registrant_contact_required' (a marketplace-domain transfer needs this to complete), ask the user for their name, phone, address, city, zip, and country, call create_registrant_contact with those, then retry with confirm=true — this is expected and not a dead end.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainYesThe Atom marketplace listing to purchase, including extension.
confirmNofalse returns a quote; true commits the charge and purchase (payment_method required).
payment_methodNoWhich rail to charge. REQUIRED when confirm=true — state this to the user before calling, never picked automatically. Ignored (and unnecessary) at the quote stage.
idempotency_keyYesClient-generated unique key; identical across the quote and confirm calls for the same intended purchase. Prevents double-charging on retry.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes
priceNoAuthoritative total price in USD (quote stage).
stageYes'quote' = price for confirmation; 'committed' = purchase completed.
domainYes
statusNoPurchase status (committed stage).
balanceNoUser's current Atom balance (quote stage).
successYes
currencyNo
order_idNoAtom marketplace order id (committed stage).
breakdownNoPrice components (quote stage): sale_price, registration_fee, vat_amount.
next_stepNoHow to complete the purchase (quote stage).
expires_atNoQuote expiry (quote stage).
saved_cardNo{brand, last4} of the saved card, if any (quote stage).
amount_chargedNoAmount actually charged in USD (committed stage).
has_saved_cardNoWhether the user has a saved/default card on file (quote stage).
payment_methodNoWhich rail was actually charged (committed stage).
idempotency_keyNo
sufficient_fundsNoWhether balance covers the price (quote stage).

TDQS

A5/5.0
Behavior5/5

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

Even though destructiveHint already signals a mutating operation, the description adds crucial context: it spends real money, requires the 'domains:register' scope, charges payment methods, returns quotes before committing, enforces idempotency, and explains the exact error paths and recovery steps. This far exceeds what annotations alone communicate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but every section carries essential operational guidance for a high-risk financial action. It is front-loaded with the core decision rule, then organized into numbered steps, error handling, and explicit prohibitions. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers prerequisites, the full quote-to-confirm sequence, user communication requirements, idempotency, insufficient funds, card failures, 3D Secure limitations, and registrant contact recovery. Given the tool's complexity and risk profile, the description is complete enough for an agent to execute correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds substantial meaning beyond the schema: confirm=false is for quoting, confirm=true requires payment_method, payment_method is ignored at quote stage, and idempotency_key must be reused across both calls. These behavioral constraints are essential and not inferable from the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

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: 'Purchase an ALREADY-LISTED Atom marketplace domain.' It clearly distinguishes itself from register_domain by explicitly stating when each applies, so an agent can tell them apart without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use conditions tied to check_domain_availability statuses and get_domain_details, names the alternative register_domain, and even explains that using this tool on a fresh domain will fail with 'not_a_marketplace_listing.' It also provides a mandatory two-step flow with no ambiguity.

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

All Atom.com — Premium Domains toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation2/5

Several tools serve the same resource+action through different payment channels (e.g., register_domain, register_domain_spt, get_domain_register_pay_link; purchase_domain, get_domain_purchase_pay_link, get_checkout_link; buy_ai_tokens, get_ai_tokens_pay_link). brainstorm_names is explicitly a duplicate of search_brandable_domains, so the set has multiple confusing overlaps despite detailed descriptions.

Naming Consistency4/5

Most tool names follow a predictable snake_case verb_noun pattern (appraise_domain, check_domain_availability, purchase_domain, screen_trademark_conflicts). Minor deviations like brainstorm_names, register_domain_spt, and get_checkout_link break the pattern slightly but remain readable and recognizable.

Tool Count3/5

Sixteen tools is right at the boundary where a tool set starts to feel heavy. Many tools are legitimately needed for discovery, purchasing, and payment routing, but the duplicate name-generation tool and the multiple payment-route variants add unnecessary bulk.

Completeness4/5

The core domain lifecycle is well covered: search/discovery, availability checks, details, appraisal, trademark screening, registrant contact, and both fresh registration and marketplace purchase paths are present. Minor gaps exist around post-purchase management, account balance visibility, and offer submission, but the main user journey has no significant dead ends.

Resources