Ada Diamonds

Request a jeweler consultation

request_consultation

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.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Customer's name
`email`	Yes	Customer's email address; the jeweler replies here
`phone`	No	Customer's phone number, if they want a call
`topic`	No	What the consultation is about
`context`	Yes	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."
`message`	No	What the customer is looking for, in their words
`llm_model`	Yes	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.
`budget_usd`	No	Approximate budget in US dollars
`product_url`	No	URL of a specific diamond, setting, or piece they are interested in
`conversation_id`	No	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.

Output Schema

TableJSON Schema

Name	Required	Description
`email`	Yes	The customer email the request was filed under
`status`	Yes	received when a request was recorded; otherwise why it was not
`message`	Yes	Human-readable outcome, including what to do next
`sandbox`	Yes	True when a sandbox credential was used: nothing was created and nobody was contacted
`reference`	Yes	Request reference, when received

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 18, 2026

addedInput schema / properties / context

Added value: +{
+  "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"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "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"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "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"
+}

changedInput schema / required

Previous value: -[
-  "email"
-]New value: +[
+  "email",
+  "context",
+  "llm_model"
+]

First observedSep 1, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already indicate this is a non-read, non-destructive operation. The description adds meaningful behavioral context: it requires a specific OAuth scope, cannot be used without customer approval, and is performed on the customer's behalf. It also implicitly warns about authorization failure. It does not describe side effects (e.g., whether a confirmation email is sent), but the OAuth requirement is the most important behavioral trait and is disclosed.

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

Conciseness4/5

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

The description is two sentences and front-loads the core action and the critical authorization requirement. It is concise and every sentence earns its place. The only minor inefficiency is that the OAuth detail could be slightly tighter, but it is essential context, so the length is justified.

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

Completeness4/5

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

Given the tool's complexity (10 params, 1 enum, output schema present), the description covers the most critical operational constraints: authorization, the analytics-only nature of `context` and `llm_model`, and the `conversation_id` sequencing rule. The output schema exists, so return values need not be described. A small gap is that it doesn't mention what happens after submission (e.g., whether the customer receives a confirmation), but the essential calling requirements are covered.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents all 10 parameters. The description adds value by explaining the `context` parameter's strict privacy rules and the `llm_model` parameter's source and fallback behavior, which are not inferable from the schema alone. It also clarifies that `conversation_id` must be echoed from a previous server response and never invented. This goes beyond the schema's basic descriptions.

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 states a specific verb ('Submit'), a clear resource ('a consultation request'), and the actor ('on the customer's behalf'). It also distinguishes itself from siblings by focusing on the consultation-request action, which none of the listed sibling tools do. The title reinforces the purpose without being a tautology.

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

Usage Guidelines4/5

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

The description clearly states a prerequisite (the `appointments:write` scope via OAuth) and that the tool cannot be used without explicit customer approval. It does not explicitly name alternative tools or when-not-to-use conditions, but the sibling list makes the alternative context clear enough. A small gap is the lack of explicit 'use this when the customer wants a consultation' guidance, but the purpose is self-evident.

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

All Ada Diamonds tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?