DouxProcess Directory

Send a request to one business

request_contact

Sends the person's request to the ONE business they chose, so it can reply to them. Only claimed listings take requests, and health businesses never do. Before calling, show the person this sentence and get their agreement: 'I agree that DouxProcess sends my name, my contact details and this request to , and only to them, so they can reply to me about it.' Set consent=true only if they agreed. Clients that support forms get a consent form instead. Never include health details, card numbers, ID numbers or passwords.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "slug": "<slug>",
      "name": "<name>",
      "details": "<details>",
      "consent": "<consent>"
    },
    "name": "request_contact"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The person's name.
`slug`	Yes	The slug from find_businesses or get_business.
`email`	No	An email address the business can reply to.
`phone`	No	Or a phone number the business can reply to.
`consent`	Yes	True only if the person read and agreed to the consent sentence.
`details`	Yes	What they need, in their words. No health details, card numbers, ID numbers or passwords.

Output Schema

Name	Required	Description	Default
`why`	No
`next`	No
`sent`	Yes
`routed`	No
`business`	No
`reference`	No
`consent_text`	No
`contact_directly`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 24, 2026

changedInput schema / properties / consent / description

Previous value: -"True only if the person agreed to the consent sentence."New value: +"True only if the person read and agreed to the consent sentence."

changedInput schema / properties / details / description

Previous value: -"What they need, in their words."New value: +"What they need, in their words. No health details, card numbers, ID numbers or passwords."

addedInput schema / properties / email / description

Added value: +"An email address the business can reply to."

addedInput schema / properties / phone / description

Added value: +"Or a phone number the business can reply to."

addedInput schema / properties / slug / description

Added value: +"The slug from find_businesses or get_business."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "business": {
+      "type": "string"
+    },
+    "consent_text": {
+      "type": "string"
+    },
+    "contact_directly": {
+      "type": "object"
+    },
+    "next": {
+      "type": "string"
+    },
+    "reference": {
+      "type": "string"
+    },
+    "routed": {
+      "type": "boolean"
+    },
+    "sent": {
+      "type": "boolean"
+    },
+    "why": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "sent"
+  ],
+  "type": "object"
+}

First observedOct 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond annotations, it discloses eligibility limits (claimed only, never health), the consent workflow, the form-based alternative, and prohibited sensitive data. This meaningfully explains the write/open-world behavior and user-agreement requirement.

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?

Purpose, eligibility, consent workflow, form alternative, and data restrictions are front-loaded and ordered by caller need. The quoted consent sentence is long but necessary because it must be shown verbatim.

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?

With 100% schema descriptions and an output schema, the remaining description burden is behavioral and workflow guidance. The description covers consent, eligibility, alternatives, and sensitive-data exclusions, leaving nothing essential for correct invocation.

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 defines all six parameters. The description still adds important semantics for consent (must reflect agreement to the exact sentence) and details (prohibited health/card/ID/password content), though it says less about slug/name/email/phone beyond the quoted consent.

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

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb ('Sends'), resource ('the person's request'), and scope ('the ONE business they chose'), and the health-business exclusion narrows applicability. However, it does not explicitly distinguish this from the sibling request_service, which could be confused with sending a request to a business.

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 states clear preconditions: only claimed listings accept requests, health businesses never do, and the person must be shown the exact consent sentence and agree before calling. It also gives the form-client alternative and the consent=true rule, leaving little inference.

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

All DouxProcess Directory 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?