agent-gateway

Request a project quote

request_project_quote

Destructive

Creates and immediately sends an external project inquiry to a private Relux Works Telegram chat for human review. Do not call it to test the connector or demonstrate MCP. Build the summary from known conversation context, ask only for missing details, obtain a real user-provided or user-confirmed reply route to the decision maker or an accountable relay agent, and show the complete draft including that route. Before calling, provide https://relux.works/en/privacy-policy/ and obtain explicit user consent. Never invent or infer contact details. The current MCP chat is not a reply route. A human replies within one business day with a recommended package and a fixed-price quote.

Input Schema

TableJSON Schema

Name	Required	Description
`market`	No	Client market or country code
`summary`	Yes	What the user wants to build or fix, current state, goals (required)
`timeline`	No	Desired timeline or deadline
`budget_usd`	No	Approximate budget in USD, if known
`client_name`	No	Name of the person or company
`project_type`	No	Closest project category
`contact_email`	No	Real, reachable decision-maker email provided or explicitly confirmed by the user. Never invent or infer it. Legacy shorthand for reply_contact with channel=email and recipient=decision_maker. Reserved example and test domains are rejected.
`reply_contact`	No	External route provided or explicitly confirmed by the user that a Relux Works human can use to reach the decision maker or a relay agent. Never invent or infer it. The current MCP session, chat, or inquiry ID does not qualify.
`consent_confirmed`	Yes	Set to true only after the user has reviewed the complete inquiry and reply route, received the privacy notice URL, and explicitly approved submission to Relux Works.
`preferred_language`	No	Language preferred for the human reply

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed5 schema fields changedJul 27, 2026

addedInput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "contact_email"
+    ]
+  },
+  {
+    "required": [
+      "reply_contact"
+    ]
+  }
+]

addedInput schema / properties / consent_confirmed

Added value: +{
+  "const": true,
+  "description": "Set to true only after the user has reviewed the complete inquiry and reply route, received the privacy notice URL, and explicitly approved submission to Relux Works.",
+  "type": "boolean"
+}

changedInput schema / properties / contact_email / description

Previous value: -"Email address a human will reply to (required)"New value: +"Real, reachable decision-maker email provided or explicitly confirmed by the user. Never invent or infer it. Legacy shorthand for reply_contact with channel=email and recipient=decision_maker. Reserved example and test domains are rejected."

addedInput schema / properties / reply_contact

Added value: +{
+  "additionalProperties": false,
+  "description": "External route provided or explicitly confirmed by the user that a Relux Works human can use to reach the decision maker or a relay agent. Never invent or infer it. The current MCP session, chat, or inquiry ID does not qualify.",
+  "properties": {
+    "channel": {
+      "enum": [
+        "email",
+        "telegram",
+        "signal",
+        "whatsapp",
+        "phone",
+        "linkedin"
+      ],
+      "type": "string"
+    },
+    "recipient": {
+      "description": "Who monitors this contact and is responsible for receiving the response.",
+      "enum": [
+        "decision_maker",
+        "relay_agent"
+      ],
+      "type": "string"
+    },
+    "value": {
+      "description": "Real address, handle, phone number, or profile URL for the selected channel.",
+      "maxLength": 500,
+      "minLength": 5,
+      "type": "string"
+    }
+  },
+  "required": [
+    "channel",
+    "value",
+    "recipient"
+  ],
+  "type": "object"
+}

changedInput schema / required

Previous value: -[
-  "contact_email",
-  "summary"
-]New value: +[
+  "summary",
+  "consent_confirmed"
+]

Changed2 schema fields changedJul 12, 2026

addedInput schema / properties / market

Added value: +{
+  "description": "Client market or country code",
+  "maxLength": 64,
+  "type": "string"
+}

addedInput schema / properties / preferred_language

Added value: +{
+  "description": "Language preferred for the human reply",
+  "maxLength": 35,
+  "type": "string"
+}

First observedJul 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

The description discloses significant behavioral traits beyond the destructiveHint annotation: it sends data externally, requires explicit user consent and privacy policy review, forbids inventing contact details, notes the current MCP chat is not a reply route, and states a human replies within one business day. This is far richer than the annotations alone.

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 a single dense paragraph where every sentence delivers essential information—purpose, misuse warning, process steps, privacy/consent, and expectations. No fluff or redundancy; it is appropriately sized for a high-stakes external action.

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?

For a complex tool with 10 parameters, nested reply_contact object, and no output schema, the description covers purpose, misuse, step-by-step submission requirements, consent, privacy policy, and the expected human follow-up. It is comprehensive enough for an agent to invoke correctly without additional external knowledge.

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 description coverage is 100%, so baseline is 3. The description adds crucial guidance for key parameters: summary must be built from known conversation context, consent_confirmed requires explicit approval after privacy notice, and contact fields must be user-provided or confirmed, never invented. It doesn't elaborate on optional fields, but they are covered by the schema.

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 action: 'Creates and immediately sends an external project inquiry to a private Relux Works Telegram chat for human review.' This clearly distinguishes it from the sibling tool get_services_pricing, which is about retrieving pricing information.

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?

It explicitly warns against misuse: 'Do not call it to test the connector or demonstrate MCP.' It also provides clear preconditions: build summary from conversation context, ask only for missing details, obtain a user-confirmed reply route, show the draft, and get explicit consent after sharing the privacy policy.

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

All agent-gateway tools Inspect

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

A4.2/5.0

Disambiguation5/5

The two tools have completely distinct purposes: one retrieves pricing/service information, the other submits a quote request. There is no overlap or ambiguity between them.

Naming Consistency5/5

Both tool names follow the same verb_noun pattern with underscores (get_services_pricing, request_project_quote), maintaining consistent and predictable naming.

Tool Count3/5

With only 2 tools, the server feels thin, but the narrow scope (pricing info and quote requests for Relux Works) makes the count borderline acceptable rather than excessive.

Completeness4/5

The tools cover the core workflow of retrieving pricing and requesting a quote, but lack features like quote status tracking or management, which is a minor gap agents can work around.

Resources

Need Help?