Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "create_checkout_link", "read_article", "request_consultation" and 4 more
⟨3 unchanged words⟩ additionalProperties":false,"properties":{"expires_at":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"ISO timestamp the link stops working","type":["string","null"]},"message":{"description":"Human-readable outcome, ⟨114 unchanged words⟩ ,"type":"number"},"url":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"The Stripe-hosted checkout URL, when ready","type":["string","null"]}},"required":["status","url", ⟨10 unchanged words⟩
⟨3 unchanged words⟩ additionalProperties":false,"properties":{"excerpt":{"anyOf":[{"typedescription":"stringOne-paragraph summary, when published"},{"type":["nullstring"}],"description":"One-paragraph summary, when publishednull"]},"found":{"description":"False when ⟨5 unchanged words⟩ ,"type":"boolean"},"markdown":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"The full article body as markdown, when found","type":["string","null"]},"slug":{"description":"The slug that was requested","type":"string"},"title":{"anyOf":[{"typedescription":"stringArticle title, when found"}
⟨3 unchanged words⟩ additionalProperties":false,"properties":{"email":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"The customer email the request was filed under","type":["string","null"]},"message":{"description":"Human-readable outcome, ⟨5 unchanged words⟩ ,"type":"string"},"reference":{"anyOf":[{"typedescription":"stringRequest reference, when received"},{"type":["nullstring"}],"description":"Request reference, when receivednull"]},"sandbox":{"description":"True when ⟨42 unchanged words⟩
⟨28 unchanged words⟩ additionalProperties":false,"properties":{"carat":{"anyOf":[{"type":"number"},{"type":"null"}],"description":"Carat weight"},"certificate":{"anyOftype":[{"typenumber":,"stringnull"]},{"typecertificate":"null"}],{"description":"Grading report number at that laboratory"},"clarity":{"anyOf":[{"type":["string"},{"type":"
⟨33 unchanged words⟩ additionalProperties":false,"properties":{"alt":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Alt text, when the catalog has one","type":["string","null"]},"url":{"description":"Image URL ⟨20 unchanged words⟩ when none is published"},"platinumUpcharge":{"anyOf":[{"type":"number"},{"type":"null"}],"description":"Additional cost to make the setting in platinum in US dollars; null when priced on request"},"priceFrom":{"anyOf":[{"type":["number"},{"type":"null"}]},"priceFrom":{"description":"Starting price of the setting alone, ⟨4 unchanged words⟩ in US dollars; null when priced on request","type":["number","null"]},"shapes":{"description":"Center-stone shapes ⟨14 unchanged words⟩ ,"type":"string"},"style":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Design style, e.g. Petite Four Prong"
⟨28 unchanged words⟩ additionalProperties":false,"properties":{"category":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Category, e.g. Bridal or Fashion"},"image":{"anyOftype":[{"additionalPropertiesstring":false,"propertiesnull":{]},"altimage":{"anyOf":[{"typeadditionalProperties":"string"}false,{"typeproperties":{"null
⟨20 unchanged words⟩ additionalProperties":false,"properties":{"excerpt":{"anyOf":[{"typedescription":"stringOne-paragraph summary, when published"},{"type":["nullstring"}],"description":"One-paragraph summary, when publishednull"]},"slug":{"description":"Article slug; ⟨73 unchanged words⟩
Changed the definition of "search_engagement_rings" and "search_jewelry"
⟨237 unchanged words⟩ :"number"},"q":{"description":"Free-textFreematchtext,one.g.the\"eastsettingwestnamebezel\"; typo tolerant, best match first","type":"string"},"shape":{ ⟨39 unchanged words⟩
Changed the definition of "create_checkout_link"
⟨265 unchanged words⟩ ["id"],"type":"object"},"maxItems":20,"minItems":1,"type":"array"},"llm_model ⟨136 unchanged words⟩
Changed the definition of "create_checkout_link", "get_company_info", "read_article" and 5 more
⟨25 unchanged words⟩ full name","type":"string"},"context":{"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.\"","type":"string"},"conversation_id":{"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.","type":"string"},"env":{"description":"sandbox returns a simulated ⟨95 unchanged words⟩ "minItems":1,"type":"array"},"llm_model":{"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.","type":"string"},"shipping_address":{"description":"Where the order ships; ⟨76 unchanged words⟩ object"}},"required":["items","shipping_address
Certificate recorded, valid to 2026-11-29
Authorization not required
First tool surface recorded: 8 tools (server version 1.0.0)
Showing the latest 7 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨235 unchanged words⟩ :"number"},"q":{"description":"Free-textFreematchtext,one.g.the\"eastproductwestnamebezel\"; typo tolerant, best match first","type":"string"},"shape":{ ⟨28 unchanged words⟩
{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"context":{"description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"","type":"string"},"conversation_id":{"description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.","type":"string"},"llm_model":{"description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.","type":"string"},"section":{"default":"all","description": ⟨37 unchanged words⟩ ","consultations"],"type":"string"}},"required":["context","llm_model"],"type":"object"}
{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"context":{"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.\"","type":"string"},"conversation_id":{"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.","type":"string"},"llm_model":{"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.","type":"string"},"slug":{"description":"Article slug from search_knowledge_base ⟨6 unchanged words⟩ type":"string"}},"required":["slug","context","llm_model"],"type":"object"}
⟨9 unchanged words⟩ US dollars","type":"number"},"context":{"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.\"","type":"string"},"conversation_id":{"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.","type":"string"},"email":{"description":"Customer's email address; the jeweler replies here","type":"string"},"llm_model":{"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.","type":"string"},"message":{"description":"What the customer is ⟨55 unchanged words⟩ type":"string"}},"required":["email","context","llm_model"],"type":"object"}
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false,"properties":{"clarity":{"description":"Clarity ⟨18 unchanged words⟩ through K","type":"string"},"context":{"description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"","type":"string"},"conversation_id":{"description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.","type":"string"},"cut":{"description":"Cut grade: Ideal, ⟨23 unchanged words⟩ "minimum":1,"type":"number"},"llm_model":{"description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.","type":"string"},"max_carat":{"description":"Maximum carat weight, ⟨72 unchanged words⟩ ","carat_desc"],"type":"string"}},"required":["context","llm_model"],"type":"object"}
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalPropertiesproperties":false{"context":{"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 \"propertiesa 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.\"","type":"string"},"conversation_id":{"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.","type":"string"},"limit":{"default":10,"description":"Maximum ⟨12 unchanged words⟩ "minimum":1,"type":"number"},"llm_model":{"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.","type":"string"},"max_price":{"description":"Maximum setting price in ⟨63 unchanged words⟩ , Three Stone","type":"string"}},"required":["context","llm_model"],"type":"object"}
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false,"properties":{"category":{"description":"Category: Bridal or Fashion","type":"string"},"context":{"description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"","type":"string"},"conversation_id":{"description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.","type":"string"},"limit":{"default":10,"description":"Maximum ⟨12 unchanged words⟩ "minimum":1,"type":"number"},"llm_model":{"description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.","type":"string"},"max_price":{"description":"Maximum price in US ⟨42 unchanged words⟩ Bracelets, Rings","type":"string"}},"required":["context","llm_model"],"type":"object"}
{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"context":{"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.\"","type":"string"},"conversation_id":{"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.","type":"string"},"limit":{"default":8,"description":"Maximum ⟨12 unchanged words⟩ "minimum":1,"type":"number"},"llm_model":{"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.","type":"string"},"query":{"description":"Topic to search for ⟨7 unchanged words⟩ type":"string"}},"required":["query","context","llm_model"],"type":"object"}