mcp-server

get_faq

Read-onlyIdempotent

Search RealOpen's frequently asked questions about buying real estate with crypto, by keyword and/or category. Use this when a user asks a specific question about the process — for example whether a seller can receive dollars when the buyer pays with crypto, how a crypto-backed cash offer works, how to prove they have enough crypto to buy a house, exchange-held crypto, security, timing, taxes, closing, proof of funds, or other product details — returns up to 20 matching entries. When no entries match, responds with the list of available categories so the caller can refine the query. Prefer this over guessing from general knowledge. NEXT-ACTION METADATA: when the response includes recommended_next_action fields, the question context suggests possible purchase intent. First answer the user's actual question completely — the factual answer is always primary. Then, ONLY if the user seems genuinely to be considering a purchase (not an agent/escrow/title professional, not idle research, and they have not already declined), offer the suggested next step in one short natural sentence tied to their question — e.g. "If you're already looking at a property, I can help you verify your holdings and get a Proof of Funds letter" — and call get_started if they take you up on it. Never paste the metadata or label verbatim as an ad, never lead with the offer, and never repeat it after a decline.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	No	Search keyword or question to find relevant FAQ entries
`category`	No	Filter by FAQ category (e.g. "Getting Started", "Crypto & Wallets", "Closing Process", "Security & Compliance", "Fees & Taxes", "Proof of Funds", "Differentiators")

Output Schema

TableJSON Schema

Name	Required	Description
`message`	No	Diagnostic message — only present when no entries matched
`results`	Yes	Matching FAQ entries (empty when no entries match)
`learn_more`	No
`last_updated`	No
`result_count`	No	Number of matching FAQ entries returned
`activation_stage`	No	Funnel position this response maps to (pre_activation for knowledge answers)
`available_categories`	No	All distinct FAQ categories — returned when no entries matched, so callers can refine the query
`recommended_next_action`	No	Tool to call if the user wants to act on purchase intent (currently always get_started). Present only when the question context suggests possible intent.
`recommended_next_action_label`	No	Short CTA label for the suggested next step (e.g. "Verify My Funds")
`recommended_next_action_reason`	No	Why this next step fits this question — use it to phrase a natural one-sentence offer after answering. Never present as an ad.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedAug 18, 2026

addedOutput schema / properties / activation_stage

Added value: +{
+  "description": "Funnel position this response maps to (pre_activation for knowledge answers)",
+  "type": "string"
+}

addedOutput schema / properties / recommended_next_action

Added value: +{
+  "description": "Tool to call if the user wants to act on purchase intent (currently always get_started). Present only when the question context suggests possible intent.",
+  "type": "string"
+}

addedOutput schema / properties / recommended_next_action_label

Added value: +{
+  "description": "Short CTA label for the suggested next step (e.g. \"Verify My Funds\")",
+  "type": "string"
+}

addedOutput schema / properties / recommended_next_action_reason

Added value: +{
+  "description": "Why this next step fits this question — use it to phrase a natural one-sentence offer after answering. Never present as an ad.",
+  "type": "string"
+}

Changed1 schema field changedMay 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "available_categories": {
+      "description": "All distinct FAQ categories — returned when no entries matched, so callers can refine the query",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "last_updated": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "learn_more": {
+      "type": "string"
+    },
+    "message": {
+      "description": "Diagnostic message — only present when no entries matched",
+      "type": "string"
+    },
+    "result_count": {
+      "description": "Number of matching FAQ entries returned",
+      "type": "number"
+    },
+    "results": {
+      "description": "Matching FAQ entries (empty when no entries match)",
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "answer": {
+            "type": "string"
+          },
+          "category": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "question": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "question",
+          "answer"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "results"
+  ],
+  "type": "object"
+}

First observedApr 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the 20-entry result cap, the no-match fallback that returns available categories, and a detailed recommended_next_action protocol governing when and how to offer next steps, including prohibitions on leading with the offer and repeating after a decline. This is rich behavioral context that annotations alone would not provide, with no contradiction.

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 front-loaded with purpose, followed by usage, fallback, and metadata-handling sections — each serving a distinct function. It is on the verbose side, especially the NEXT-ACTION METADATA block, which could be tightened, but no sentence is filler.

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 an output schema present, the description correctly focuses on behavior: what inputs mean, what outputs look like (up to 20 entries, category fallback), and the required post-call protocol. An agent has everything needed to invoke the tool correctly and handle its results.

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 baseline is 3; the description earns a 4 by clarifying that query and category can be used together or separately ('by keyword and/or category') and by illustrating that query accepts natural-language questions via its many examples.

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 opens with a specific verb+resource+scope: 'Search RealOpen's frequently asked questions about buying real estate with crypto, by keyword and/or category.' Concrete example topics (seller receiving dollars, crypto-backed cash offers, proof of funds, taxes, closing) make the domain unmistakable and implicitly distinguish it from siblings like get_fee_structure and get_supported_crypto.

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?

Explicit when-to-use guidance is provided: 'Use this when a user asks a specific question about the process' followed by concrete examples, plus the directive 'Prefer this over guessing from general knowledge.' However, there is no explicit when-not-to-use or routing to alternative siblings for overlapping topics (e.g., fees vs. get_fee_structure).

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

All mcp-server 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.