C4C: Mortgage Industry Regulations

Start playbook

start_playbook

Read-onlyIdempotent

Returns one playbook's full workflow instructions, its stages, the stage reference names and the rule-kit version: the Fannie Mae AI lender letter (LL-2026-04) P&P review, or FHA, VA or USDA loan-file QC. Input: the playbook id; an unknown id returns unknown_playbook with valid_ids. Playbook tools accept only ids and reference names, no document text; the user's P&Ps and loan files stay in their own chat.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes	Playbook id: one of fnma-ai-lender-letter, fha-underwriting-qc, va-loan-qc, usda-loan-qc.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No	The playbook id.
`kit`	No	The rule kit ({kind, source, version, load_with}).
`hint`	No	On an error: the server's explanation.
`note`	No	A note on this result.
`error`	No	Present only on an error or refusal: not_found, ambiguous, unparsed, empty_terms, unknown_playbook, unknown_reference, offset_out_of_range, daily_capacity_reached.
`title`	No	The playbook's name.
`notice`	No	Terms notice: research use only, not legal advice.
`resets`	No	On daily_capacity_reached: when capacity resets (00:00 UTC).
`stages`	No	The workflow's stages.
`privacy`	No	How user material is handled.
`version`	No	The playbook's version.
`fallback`	No	On daily_capacity_reached: where the full corpus can be downloaded.
`guidance`	No	On a refusal or empty search: the server's explanation.
`valid_ids`	No	On unknown_playbook: the valid ids.
`references`	No	The playbook's reference names.
`instructions`	No	The playbook's workflow instructions.
`user_provides`	No	What the user supplies.
`load_reference_with`	No	How a reference is loaded, or null when there are none.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 27, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "description": "start_playbook result.",
+  "properties": {
+    "error": {
+      "description": "Present only on an error or refusal: not_found, ambiguous, unparsed, empty_terms, unknown_playbook, unknown_reference, offset_out_of_range, daily_capacity_reached.",
+      "type": "string"
+    },
+    "fallback": {
+      "description": "On daily_capacity_reached: where the full corpus can be downloaded.",
+      "type": "string"
+    },
+    "guidance": {
+      "description": "On a refusal or empty search: the server's explanation.",
+      "type": "string"
+    },
+    "hint": {
+      "description": "On an error: the server's explanation.",
+      "type": "string"
+    },
+    "id": {
+      "description": "The playbook id.",
+      "type": "string"
+    },
+    "instructions": {
+      "description": "The playbook's workflow instructions."
+    },
+    "kit": {
+      "description": "The rule kit ({kind, source, version, load_with})."
+    },
+    "load_reference_with": {
+      "description": "How a reference is loaded, or null when there are none.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "note": {
+      "description": "A note on this result.",
+      "type": "string"
+    },
+    "notice": {
+      "description": "Terms notice: research use only, not legal advice.",
+      "type": "string"
+    },
+    "privacy": {
+      "description": "How user material is handled."
+    },
+    "references": {
+      "description": "The playbook's reference names.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "resets": {
+      "description": "On daily_capacity_reached: when capacity resets (00:00 UTC).",
+      "type": "string"
+    },
+    "stages": {
+      "description": "The workflow's stages."
+    },
+    "title": {
+      "description": "The playbook's name.",
+      "type": "string"
+    },
+    "user_provides": {
+      "description": "What the user supplies."
+    },
+    "valid_ids": {
+      "description": "On unknown_playbook: the valid ids.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "version": {
+      "description": "The playbook's version."
+    }
+  },
+  "type": "object"
+}

First observedSep 26, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. Beyond that the description discloses the error contract ('unknown id returns `unknown_playbook` with `valid_ids`') and an important scope constraint: playbook tools accept only ids and reference names, never document text, with P&Ps and loan files staying in the user's chat. That is real behavioral context not available in the schema or annotations.

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 return payload is front-loaded, followed by input and then the no-document-text constraint. It is dense but every clause carries information; a small amount of unpacking into separate sentences would improve scanability.

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?

An output schema exists, so return values need not be explained, yet the description still covers the payload shape, the error case, and the data-boundary constraint. It is essentially complete for a single-parameter read tool, with only sibling differentiation left unaddressed.

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

Parameters3/5

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

Schema description coverage is 100% and the single `id` parameter already documents its pattern, max length and the four valid values, so the baseline is 3. The description repeats the id-based input model but adds no format or syntax detail beyond the schema.

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 description states a specific verb and resource ('Returns one playbook's full workflow instructions, its stages, the stage reference names and the rule-kit version') and enumerates the covered playbook families. It does not, however, explicitly distinguish itself from siblings like list_playbooks, get_playbook_kit or get_playbook_reference, so the agent must infer the difference.

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

Usage Guidelines3/5

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

It specifies the required input ('the playbook `id`') and the failure mode for an unknown id, which implies when the tool applies. But it never says when to choose this over list_playbooks (to discover ids) or the get_playbook_* siblings (to fetch sub-parts), leaving the routing to inference.

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

All C4C: Mortgage Industry Regulations 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.