Skip to main content
Glama

C4C: Mortgage Industry Regulations

by com.claudeforcompliance
OverviewDiscussionsAdmin

Verify quote

verify_quote
Read-onlyIdempotent

Checks whether a passage appears in a regulator's source document; accepts text from any source. Inputs: text (up to 5,000 words); optional register_id (without it, up to 3 candidate documents are located by search). outcome is one of: exact (contiguous in the source, quote marks and dashes as the source writes them; a line break counts as a space); normalized (matches after folding quote and dash typography, typography_folded; ignoring page footers or running heads, furniture_ignored; spacing where the stored source splits or joins words, spacing_ignored; or added list markers, list_markers_ignored); composed (every word is in the source, in source order, but from non-contiguous pieces, as with an overview or an ellipsis; omissions lists the short source phrases skipped between pieces); not_found (no source support; unsupported lists the unsupported spans, and on a near miss differences gives the closest source text, the source words the text lacks and the words it adds); not_checked (over 5,000 words). coverage is the share of words found. checked_against names the documents checked (document, edition, retrieval date; ids in checked_snapshot_ids); matched_against names the one matched, matched_register_id / matched_obligation_id the stored text containing the passage. matched_version is current; superseded (the text is a prior version of the rule; superseded_by is the current register); or update-18-optional (HUD's Update 18 revision of an FHA 4000.1 section, optional until mandatory_date; in_force_obligation_id is the text in force by default). obligation_currency lists currency signals on the obligation holding the text (e.g. superseded-in-part). rescinded: true (with rescinded_by) means the passage is text a later issuance removed or replaced.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
register_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
hintNoOn an error: the server's explanation.
noteNoA note on this result.
errorNoPresent only on an error or refusal: not_found, ambiguous, unparsed, empty_terms, unknown_playbook, unknown_reference, offset_out_of_range, daily_capacity_reached.
limitNoOn not_checked: the word limit.
wordsNoOn not_checked: the word count.
noticeNoTerms notice: research use only, not legal advice.
reasonNoOn not_checked: too_long.
resetsNoOn daily_capacity_reached: when capacity resets (00:00 UTC).
outcomeNoexact: contiguous in the source; normalized: matches after typography, spacing, footer or list-marker folding; composed: all words in source order, non-contiguous; not_found: no source support; not_checked: over 5,000 words.
coverageNoShare of the text's words found in the source (0 to 1).
elisionsNoOn composed: gaps (marked or not).
fallbackNoOn daily_capacity_reached: where the full corpus can be downloaded.
guidanceNoOn a refusal or empty search: the server's explanation.
page_urlNoThe matched section's page on claudeforcompliance.com.
segmentsNoOn composed: source pieces the text is assembled from.
omissionsNoOn composed: short source phrases skipped between pieces.
source_urlNoThe regulator's URL for the matched section's document.
differencesNoOn a near miss: {closest_source, missing_from_quote, extra_in_quote}.
register_idNoEchoed on not_found.
unsupportedNoOn not_found: spans with no source support.
superseded_byNoOn superseded: the current register.
mandatory_dateNoOn an Update 18 revision: when it becomes mandatory.
checked_againstNoSource documents checked (document, edition, retrieval date).
matched_againstNoThe checked document the text matched.
matched_versionNocurrent, superseded (a prior version) or update-18-optional.
spacing_ignoredNoOnly spacing differs.
furniture_ignoredNoA page footer or running head was ignored.
typography_foldedNoMatched after folding quotes and dashes.
matched_register_idNoThe register whose stored text contains the passage.
checked_snapshot_idsNoSnapshot ids checked.
list_markers_ignoredNoAdded list markers were ignored.
also_in_obligation_idNoOn a match in an amending issuance: the amended obligation that also carries the text.
matched_obligation_idNoThe obligation whose stored text contains the passage.
superseded_register_idNoOn superseded: the register holding the prior text.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / page_url
      Added value: +{
+  "description": "The matched section's page on claudeforcompliance.com.",
+  "type": "string"
+}
    • addedOutput schema / properties / source_url
      Added value: +{
+  "description": "The regulator's URL for the matched section's document.",
+  "type": "string"
+}
  2. Changed4 schema fields changed
    • addedOutput schema / properties / also_in_obligation_id
      Added value: +{
+  "description": "On a match in an amending issuance: the amended obligation that also carries the text.",
+  "type": "string"
+}
    • addedOutput schema / properties / matched_against
      Added value: +{
+  "description": "The checked document the text matched.",
+  "type": "string"
+}
    • addedOutput schema / properties / matched_obligation_id
      Added value: +{
+  "description": "The obligation whose stored text contains the passage.",
+  "type": "string"
+}
    • addedOutput schema / properties / matched_register_id
      Added value: +{
+  "description": "The register whose stored text contains the passage.",
+  "type": "string"
+}
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "description": "verify_quote result.",
+  "properties": {
+    "checked_against": {
+      "description": "Source documents checked (document, edition, retrieval date)."
+    },
+    "checked_snapshot_ids": {
+      "description": "Snapshot ids checked."
+    },
+    "coverage": {
+      "description": "Share of the text's words found in the source (0 to 1).",
+      "type": "number"
+    },
+    "differences": {
+      "description": "On a near miss: {closest_source, missing_from_quote, extra_in_quote}."
+    },
+    "elisions": {
+      "description": "On composed: gaps (marked or not).",
+      "type": "number"
+    },
+    "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"
+    },
+    "furniture_ignored": {
+      "description": "A page footer or running head was ignored.",
+      "type": "boolean"
+    },
+    "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"
+    },
+    "limit": {
+      "description": "On not_checked: the word limit.",
+      "type": "number"
+    },
+    "list_markers_ignored": {
+      "description": "Added list markers were ignored.",
+      "type": "boolean"
+    },
+    "mandatory_date": {
+      "description": "On an Update 18 revision: when it becomes mandatory.",
+      "type": "string"
+    },
+    "matched_version": {
+      "description": "current, superseded (a prior version) or update-18-optional.",
+      "type": "string"
+    },
+    "note": {
+      "description": "A note on this result.",
+      "type": "string"
+    },
+    "notice": {
+      "description": "Terms notice: research use only, not legal advice.",
+      "type": "string"
+    },
+    "omissions": {
+      "description": "On composed: short source phrases skipped between pieces."
+    },
+    "outcome": {
+      "description": "exact: contiguous in the source; normalized: matches after typography, spacing, footer or list-marker folding; composed: all words in source order, non-contiguous; not_found: no source support; not_checked: over 5,000 words.",
+      "enum": [
+        "exact",
+        "normalized",
+        "composed",
+        "not_found",
+        "not_checked"
+      ],
+      "type": "string"
+    },
+    "reason": {
+      "description": "On not_checked: too_long.",
+      "type": "string"
+    },
+    "register_id": {
+      "description": "Echoed on not_found.",
+      "type": "string"
+    },
+    "resets": {
+      "description": "On daily_capacity_reached: when capacity resets (00:00 UTC).",
+      "type": "string"
+    },
+    "segments": {
+      "description": "On composed: source pieces the text is assembled from.",
+      "type": "number"
+    },
+    "spacing_ignored": {
+      "description": "Only spacing differs.",
+      "type": "boolean"
+    },
+    "superseded_by": {
+      "description": "On superseded: the current register.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "superseded_register_id": {
+      "description": "On superseded: the register holding the prior text.",
+      "type": "string"
+    },
+    "typography_folded": {
+      "description": "Matched after folding quotes and dashes.",
+      "type": "boolean"
+    },
+    "unsupported": {
+      "description": "On not_found: spans with no source support."
+    },
+    "words": {
+      "description": "On not_checked: the word count.",
+      "type": "number"
+    }
+  },
+  "type": "object"
+}
  4. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral context beyond that: the 5,000-word ceiling that yields not_checked, and the fallback search behavior when `register_id` is omitted.

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

Conciseness3/5

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

The purpose and inputs are front-loaded, which is good, but the bulk of the text is a dense run-on enumeration of output fields and enum values (outcome, coverage, checked_against, matched_version, rescinded, etc.) crammed into a single paragraph. Since an output schema exists, much of this enumeration risks duplicating structured data.

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?

Inputs, limits, and fallback behavior are all present, and the tool is a read-only check with no destructive side effects to warn about. With an output schema present, the description arguably over-delivers on return values rather than under-delivering.

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 0%, so the description must carry the load, and it does: `text` is bounded at 5,000 words and `register_id` is optional with a defined fallback ('up to 3 candidate documents are located by search'). Format expectations for `register_id` (an id) are only loosely implied.

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 opening sentence gives a specific verb+resource ('checks whether a passage appears in a regulator's source document') and adds scope ('accepts text from any source'). It is clearly distinguishable from siblings like lookup_citation or find_in_section, though it never names them explicitly.

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?

Usage context is implied rather than stated: it explains what happens with and without `register_id` (up to 3 candidate documents located by search), which hints at when to supply it. There is no explicit when-to-use/when-not or routing to an alternative sibling tool.

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 toolsInspect
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