Ada Diamonds
Live lab grown diamond inventory, engagement ring settings, fine jewelry, and diamond buying guides.
Sollte ich dies verwenden
Qualität und Sicherheit
A
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
~7,068Tokens (Tool-Definitionen)
~10.4 KBTypische Antwortgröße
Erhebliche Auswirkung auf die Aufmerksamkeit (5.52% von 128k Kontext)
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"ada-diamonds": {
"url": "https://www.adadiamonds.com/mcp"
}
}
}Remote-Endpunkte
https://www.adadiamonds.com/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (8)
🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟢search_diamonds(shape, min_carat, max_carat, min_price, max_price, ...)
Search Ada Diamonds' live loose lab grown diamond inventory by shape, carat weight, price, color, clarity, and cut. Returns currently available stones with their grading report numbers and product URLs. Use this for any question about what diamond a budget can buy. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.
Eingabe-Schema
{
"type": "object",
"properties": {
"shape": {
"description": "Cut shape: Round, Oval, Cushion, Emerald, Pear, Radiant, Asscher, Princess, or Marquise",
"type": "string"
},
"min_carat": {
"description": "Minimum carat weight, e.g. 1 or 1.5",
"type": "number"
},
"max_carat": {
"description": "Maximum carat weight, e.g. 2",
"type": "number"
},
"min_price": {
"description": "Minimum price of the loose stone in US dollars",
"type": "number"
},
"max_price": {
"description": "Maximum price of the loose stone in US dollars",
"type": "number"
},
"color": {
"description": "Color grade, D (colorless) through K",
"type": "string"
},
"clarity": {
"description": "Clarity grade: FL, IF, VVS1, VVS2, VS1, VS2, SI1, or SI2",
"type": "string"
},
"cut": {
"description": "Cut grade: Ideal, Excellent, or Very Good",
"type": "string"
},
"sort": {
"description": "Result order: price_asc (default relevance), price_desc, carat_asc, or carat_desc",
"type": "string",
"enum": [
"price_asc",
"price_desc",
"carat_asc",
"carat_desc"
]
},
"limit": {
"default": 10,
"description": "Maximum number of results to return, 1 to 50 (default 10)",
"type": "number",
"minimum": 1,
"maximum": 50
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"const": "diamonds",
"description": "Which catalog the results come from"
},
"query": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "The filters that were applied (only the ones you sent)"
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many catalog entries matched before the limit"
},
"shown": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many entries are in `items`"
},
"browseUrl": {
"type": "string",
"description": "Web page listing the full catalog for this search"
},
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Ada Diamonds stock id"
},
"name": {
"type": "string",
"description": "Display name, e.g. \"1.52 ct Oval, F, VS1\""
},
"url": {
"type": "string",
"description": "Product page URL"
},
"price": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Price of the loose stone in US dollars; null when priced on request"
},
"carat": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Carat weight"
},
"shape": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Cut shape, e.g. Oval"
},
"color": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Color grade, D through K"
},
"clarity": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Clarity grade, FL through SI2"
},
"cut": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Cut grade, e.g. Ideal"
},
"lab": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Grading laboratory, IGI or GIA"
},
"certificate": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Grading report number at that laboratory"
},
"measurements": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Length x width x depth in millimetres"
}
},
"required": [
"id",
"name",
"url",
"price",
"carat",
"shape",
"color",
"clarity",
"cut",
"lab",
"certificate",
"measurements"
],
"additionalProperties": false
},
"description": "The matching entries, best match first"
}
},
"required": [
"kind",
"query",
"total",
"shown",
"browseUrl",
"items"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢search_engagement_rings(shape, style, type, min_price, max_price, ...)
Search Ada Diamonds' engagement ring settings by center-stone shape, style, and setting price. Setting prices exclude the center diamond — pair with search_diamonds to quote a complete ring. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.
Eingabe-Schema
{
"type": "object",
"properties": {
"shape": {
"description": "Center-stone shape the setting must accommodate, e.g. Oval",
"type": "string"
},
"style": {
"description": "Design style, e.g. Petite Four Prong, Trellis, Bezel",
"type": "string"
},
"type": {
"description": "Setting type, e.g. Solitaire, Halo, Three Stone",
"type": "string"
},
"min_price": {
"description": "Minimum setting price in US dollars, excluding the center diamond",
"type": "number"
},
"max_price": {
"description": "Maximum setting price in US dollars, excluding the center diamond",
"type": "number"
},
"q": {
"description": "Free-text match on the setting name",
"type": "string"
},
"limit": {
"default": 10,
"description": "Maximum number of results to return, 1 to 50 (default 10)",
"type": "number",
"minimum": 1,
"maximum": 50
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"const": "engagement-rings",
"description": "Which catalog the results come from"
},
"query": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "The filters that were applied (only the ones you sent)"
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many catalog entries matched before the limit"
},
"shown": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many entries are in `items`"
},
"browseUrl": {
"type": "string",
"description": "Web page listing the full catalog for this search"
},
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"sku": {
"type": "string",
"description": "Setting SKU, e.g. AD-066"
},
"title": {
"type": "string",
"description": "Setting name"
},
"url": {
"type": "string",
"description": "Product page URL"
},
"shapes": {
"type": "array",
"items": {
"type": "string"
},
"description": "Center-stone shapes the setting accommodates"
},
"style": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Design style, e.g. Petite Four Prong"
},
"type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Setting type, e.g. Solitaire, Halo, Three Stone"
},
"priceFrom": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Starting price of the setting alone, excluding the center diamond in US dollars; null when priced on request"
},
"platinumUpcharge": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Additional cost to make the setting in platinum in US dollars; null when priced on request"
},
"image": {
"anyOf": [
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Image URL on the Ada Diamonds CDN"
},
"alt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Alt text, when the catalog has one"
}
},
"required": [
"url",
"alt"
],
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Primary product image, or null when none is published"
}
},
"required": [
"sku",
"title",
"url",
"shapes",
"style",
"type",
"priceFrom",
"platinumUpcharge",
"image"
],
"additionalProperties": false
},
"description": "The matching entries, best match first"
}
},
"required": [
"kind",
"query",
"total",
"shown",
"browseUrl",
"items"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢search_jewelry(category, type, shape, min_price, max_price, ...)
Search Ada Diamonds' fine jewelry — wedding bands, earrings, necklaces, bracelets, and fashion rings — by category, type, diamond shape, and price. MCP Apps-enabled: hosts that support MCP Apps render the results as an interactive card grid.
Eingabe-Schema
{
"type": "object",
"properties": {
"category": {
"description": "Category: Bridal or Fashion",
"type": "string"
},
"type": {
"description": "Type, e.g. Wedding Bands, Earrings, Necklaces, Bracelets, Rings",
"type": "string"
},
"shape": {
"description": "Diamond shape used in the piece, e.g. Round",
"type": "string"
},
"min_price": {
"description": "Minimum price in US dollars",
"type": "number"
},
"max_price": {
"description": "Maximum price in US dollars",
"type": "number"
},
"q": {
"description": "Free-text match on the product name",
"type": "string"
},
"limit": {
"default": 10,
"description": "Maximum number of results to return, 1 to 50 (default 10)",
"type": "number",
"minimum": 1,
"maximum": 50
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"const": "jewelry",
"description": "Which catalog the results come from"
},
"query": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "The filters that were applied (only the ones you sent)"
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many catalog entries matched before the limit"
},
"shown": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many entries are in `items`"
},
"browseUrl": {
"type": "string",
"description": "Web page listing the full catalog for this search"
},
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"sku": {
"type": "string",
"description": "Product SKU"
},
"title": {
"type": "string",
"description": "Product name"
},
"url": {
"type": "string",
"description": "Product page URL"
},
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Category, e.g. Bridal or Fashion"
},
"type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Type, e.g. Wedding Bands, Earrings, Necklaces"
},
"shapes": {
"type": "array",
"items": {
"type": "string"
},
"description": "Diamond shapes used in the piece"
},
"priceFrom": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Lowest price across the piece's options in US dollars; null when priced on request"
},
"priceMax": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Highest price across the piece's options; null when there is one price in US dollars; null when priced on request"
},
"image": {
"anyOf": [
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Image URL on the Ada Diamonds CDN"
},
"alt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Alt text, when the catalog has one"
}
},
"required": [
"url",
"alt"
],
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Primary product image, or null when none is published"
}
},
"required": [
"sku",
"title",
"url",
"category",
"type",
"shapes",
"priceFrom",
"priceMax",
"image"
],
"additionalProperties": false
},
"description": "The matching entries, best match first"
}
},
"required": [
"kind",
"query",
"total",
"shown",
"browseUrl",
"items"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢search_knowledge_base(query, limit, context, llm_model, conversation_id)
Search Ada Diamonds' published guides on lab grown diamonds — the 4Cs, CVD vs HPHT growth, shape guides, certification, and buying advice. Returns article summaries and markdown URLs. Use read_article to get an article's full text.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Topic to search for, matched against article titles, summaries, and slugs"
},
"limit": {
"default": 8,
"description": "Maximum number of results to return, 1 to 25 (default 8)",
"type": "number",
"minimum": 1,
"maximum": 25
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"query",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"const": "articles",
"description": "Always \"articles\""
},
"query": {
"type": "string",
"description": "The search terms that were used"
},
"total": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991,
"description": "How many articles are in `items`"
},
"browseUrl": {
"type": "string",
"description": "Web page listing every guide"
},
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Article slug; pass it to read_article"
},
"title": {
"type": "string",
"description": "Article title"
},
"excerpt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "One-paragraph summary, when published"
},
"url": {
"type": "string",
"description": "Article page URL; append .md for markdown"
}
},
"required": [
"slug",
"title",
"excerpt",
"url"
],
"additionalProperties": false
},
"description": "Matching articles"
}
},
"required": [
"kind",
"query",
"total",
"browseUrl",
"items"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢read_article(slug, context, llm_model, conversation_id)
Fetch the full markdown text of one Ada Diamonds knowledge base article by slug. Use search_knowledge_base first if you don't know the slug.
Eingabe-Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Article slug from search_knowledge_base, e.g. \"cvd-lab-diamonds\" or \"lab-diamond-shapes-guide\""
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"slug",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"found": {
"type": "boolean",
"description": "False when no article has that slug"
},
"slug": {
"type": "string",
"description": "The slug that was requested"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Article title, when found"
},
"excerpt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "One-paragraph summary, when published"
},
"url": {
"type": "string",
"description": "Article page URL"
},
"markdown": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The full article body as markdown, when found"
}
},
"required": [
"found",
"slug",
"title",
"excerpt",
"url",
"markdown"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_company_info(section, context, llm_model, conversation_id)
Contact details, showroom address and hours, how consultations work, and what Ada Diamonds sells. Use this to answer questions about the business rather than about a product.
Eingabe-Schema
{
"type": "object",
"properties": {
"section": {
"default": "all",
"description": "Which part to return as text: contact (phone, email, hours, website), showrooms (addresses and hours), consultations (how remote and in-person consultations work), or all (default). The structured result always carries every section.",
"type": "string",
"enum": [
"all",
"contact",
"showrooms",
"consultations"
]
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Legal company name"
},
"description": {
"type": "string",
"description": "What Ada Diamonds sells and how it works"
},
"phone": {
"type": "string",
"description": "Main phone number"
},
"email": {
"type": "string",
"description": "Customer email address"
},
"hours": {
"type": "string",
"description": "Business hours"
},
"website": {
"type": "string",
"description": "Website URL"
},
"inquiryUrl": {
"type": "string",
"description": "Page where a customer starts a consultation"
},
"showrooms": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Showroom name"
},
"streetAddress": {
"type": "string",
"description": "Street address"
},
"addressLocality": {
"type": "string",
"description": "City"
},
"addressRegion": {
"type": "string",
"description": "State"
},
"postalCode": {
"type": "string",
"description": "ZIP code"
},
"telephone": {
"type": "string",
"description": "Showroom phone number"
},
"hours": {
"type": "string",
"description": "Showroom hours"
},
"appointmentRequired": {
"type": "boolean",
"description": "Whether visits are by appointment"
}
},
"required": [
"name",
"streetAddress",
"addressLocality",
"addressRegion",
"postalCode",
"telephone",
"hours",
"appointmentRequired"
],
"additionalProperties": false
},
"description": "Physical showrooms"
}
},
"required": [
"name",
"description",
"phone",
"email",
"hours",
"website",
"inquiryUrl",
"showrooms"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟡create_checkout_link(items, shipping_address, buyer_email, buyer_name, env, ...)
Assemble a cart and get a Stripe-hosted checkout URL the customer opens to pay; no card data passes through the agent. Item ids come from the search tools (`diamond:<report>`, `setting:<slug>`, `jewelry:<slug>`); a complete ring is one setting plus one diamond. Needs the shipping address (prices tax and shipping into the link). Expires after 24 hours. No credential needed. Without a production credential this tool runs in the sandbox: the link is simulated and no Stripe session is created. Pass `env: "production"` when the customer actually wants to buy — that returns a live, payable link.
Eingabe-Schema
{
"type": "object",
"properties": {
"items": {
"minItems": 1,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Catalog item id: `diamond:<report number>`, `setting:<slug>`, or `jewelry:<slug>` (from search_diamonds / search_engagement_rings / search_jewelry results)"
},
"quantity": {
"default": 1,
"description": "Quantity, 1-10 (diamonds are always 1)",
"type": "integer",
"minimum": 1,
"maximum": 10
}
},
"required": [
"id"
]
},
"description": "Items to buy; a complete ring is one setting plus one diamond"
},
"shipping_address": {
"type": "object",
"properties": {
"name": {
"description": "Recipient name",
"type": "string"
},
"line_one": {
"type": "string",
"description": "Street address, line 1"
},
"line_two": {
"description": "Street address, line 2",
"type": "string"
},
"city": {
"type": "string",
"description": "City"
},
"state": {
"type": "string",
"description": "State or region code, e.g. NY"
},
"postal_code": {
"type": "string",
"description": "Postal code"
},
"country": {
"type": "string",
"description": "Two-letter country code, e.g. US"
},
"phone_number": {
"description": "Recipient phone number",
"type": "string"
}
},
"required": [
"line_one",
"city",
"state",
"postal_code",
"country"
],
"description": "Where the order ships; used to price tax and shipping into the link"
},
"buyer_email": {
"description": "Buyer email for the receipt; Stripe collects it on the payment page when omitted",
"type": "string"
},
"buyer_name": {
"description": "Buyer full name",
"type": "string"
},
"env": {
"description": "sandbox returns a simulated link and creates no Stripe session; production mints a live, payable Stripe Checkout link. Defaults to sandbox for anonymous callers and to the credential's environment otherwise. A sandbox credential is always sandbox.",
"type": "string",
"enum": [
"production",
"sandbox"
]
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"items",
"shipping_address",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"needs_input",
"failed"
],
"description": "ready when a payable link was created; needs_input lists what is missing"
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The Stripe-hosted checkout URL, when ready"
},
"expires_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "ISO timestamp the link stops working"
},
"sandbox": {
"type": "boolean",
"description": "True when the link is simulated (sandbox): nothing is payable and no Stripe session was created. False means the link is live and payable."
},
"subtotal_usd": {
"type": "number",
"description": "Items subtotal in US dollars"
},
"shipping_usd": {
"type": "number",
"description": "Shipping in US dollars (0 = free insured FedEx)"
},
"tax_usd": {
"type": "number",
"description": "Sales tax in US dollars for the given address"
},
"total_usd": {
"type": "number",
"description": "Total the buyer pays in US dollars"
},
"problems": {
"type": "array",
"items": {
"type": "string"
},
"description": "What blocks the link when status is needs_input"
},
"message": {
"type": "string",
"description": "Human-readable outcome, including the link when ready"
}
},
"required": [
"status",
"url",
"expires_at",
"sandbox",
"subtotal_usd",
"shipping_usd",
"tax_usd",
"total_usd",
"problems",
"message"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟡request_consultation(email, name, phone, topic, message, ...)
Submit a consultation request on the customer's behalf. Requires the `appointments:write` scope, which the customer grants through Ada's OAuth authorization flow — this tool cannot be used without their explicit approval.
Eingabe-Schema
{
"type": "object",
"properties": {
"email": {
"type": "string",
"description": "Customer's email address; the jeweler replies here"
},
"name": {
"description": "Customer's name",
"type": "string"
},
"phone": {
"description": "Customer's phone number, if they want a call",
"type": "string"
},
"topic": {
"description": "What the consultation is about",
"type": "string",
"enum": [
"engagement_ring",
"loose_diamond",
"wedding_band",
"fine_jewelry",
"custom_design",
"other"
]
},
"message": {
"description": "What the customer is looking for, in their words",
"type": "string"
},
"budget_usd": {
"description": "Approximate budget in US dollars",
"type": "number"
},
"product_url": {
"description": "URL of a specific diamond, setting, or piece they are interested in",
"type": "string"
},
"context": {
"type": "string",
"description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
}
},
"required": [
"email",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"received",
"not_authorized",
"invalid",
"failed"
],
"description": "received when a request was recorded; otherwise why it was not"
},
"reference": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Request reference, when received"
},
"email": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The customer email the request was filed under"
},
"sandbox": {
"type": "boolean",
"description": "True when a sandbox credential was used: nothing was created and nobody was contacted"
},
"message": {
"type": "string",
"description": "Human-readable outcome, including what to do next"
}
},
"required": [
"status",
"reference",
"email",
"sandbox",
"message"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Community
Nachweis
Aktuelle Beobachtungen
verifiziertVersion nicht aufgezeichnet8 Tools
verifiziertVersion nicht aufgezeichnet8 Tools