Skip to main content
Glama
Sign In

CMD+RVL Receipts

by com.cmdrvl
OverviewDiscussionsAdmin

Verify a deal counterparty (roster)

verify_counterparty
Read-onlyIdempotent

Adjudicate 'who is the on deal X' against the SEC 10-D counterparty roster (today: master and special servicer). A SINGLE-SOURCE roster fact. Master is the roster party, NOT the ABS-EE tape's primary servicer. Pass claimed_name: CONFIRM/DENY under the ledger's name normalization, never fuzzy. Says WHO the party is, not that a loan is in special servicing. Unknown deal or role: UNVERIFIED.

Input Schema

NameRequiredDescriptionDefault
dealYesDeal name or alias, e.g. 'WFCM 2020-C58'.
roleNoDefault special_servicer. Full definitions ride each receipt's field_definition.
claimed_nameNoName to adjudicate (normalized comparison).

Output Schema

NameRequiredDescriptionDefault
as_ofYes
claimYesAdjudication: claimed_value, tolerance_*, within_tolerance, rationale.
messageYes
receiptYessf-receipt 0.3; schema https://cmdrvl.com/schemas/sf-receipt/v0/schema.json; context https://cmdrvl.com/contexts/obs-receipt/v0/context.json
claim_verdictYesCaller-claim verdict; DENY only here.
resolved_dealYesDeal resolution: matched, id, cik, candidates.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed23 schema fields changed
    • changedOutput schema / properties / claim / additionalProperties
      Previous value: -falseNew value: +true
    • changedOutput schema / properties / claim / description
      Previous value: -"Claim-adjudication detail."New value: +"Adjudication: claimed_value, tolerance_*, within_tolerance, rationale."
    • removedOutput schema / properties / claim / properties / abs_diff
      Removed value: -{
-  "type": [
-    "number",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / properties / basis
      Removed value: -{
-  "anyOf": [
-    {
-      "$ref": "#/properties/claim/properties/claimed_value/anyOf/0"
-    },
-    {
-      "type": "null"
-    }
-  ]
-}
    • removedOutput schema / properties / claim / properties / claimed_basis
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / properties / claimed_unit
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / properties / claimed_value
      Removed value: -{
-  "anyOf": [
-    {
-      "type": [
-        "number",
-        "string"
-      ]
-    },
-    {
-      "type": "null"
-    }
-  ]
-}
    • removedOutput schema / properties / claim / properties / claimed_value_date
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / properties / rationale
      Removed value: -{
-  "type": "string"
-}
    • removedOutput schema / properties / claim / properties / rel_bps_diff
      Removed value: -{
-  "type": [
-    "number",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / properties / tolerance_kind
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / properties / tolerance_used
      Removed value: -{
-  "type": [
-    "number",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / properties / within_tolerance
      Removed value: -{
-  "type": [
-    "boolean",
-    "null"
-  ]
-}
    • removedOutput schema / properties / claim / required
      Removed value: -[
-  "claimed_value",
-  "tolerance_kind",
-  "tolerance_used",
-  "abs_diff",
-  "rel_bps_diff",
-  "within_tolerance",
-  "basis",
-  "rationale"
-]
    • changedOutput schema / properties / resolved_deal / additionalProperties
      Previous value: -falseNew value: +true
    • addedOutput schema / properties / resolved_deal / description
      Added value: +"Deal resolution: matched, id, cik, candidates."
    • removedOutput schema / properties / resolved_deal / properties / candidates
      Removed value: -{
-  "description": "Suggested deal ids when unmatched/ambiguous.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
    • removedOutput schema / properties / resolved_deal / properties / cik
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedOutput schema / properties / resolved_deal / properties / id
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedOutput schema / properties / resolved_deal / properties / matched
      Removed value: -{
-  "type": "boolean"
-}
    • removedOutput schema / properties / resolved_deal / properties / name
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedOutput schema / properties / resolved_deal / properties / query
      Removed value: -{
-  "type": "string"
-}
    • removedOutput schema / properties / resolved_deal / required
      Removed value: -[
-  "query",
-  "matched",
-  "id",
-  "name",
-  "cik",
-  "candidates"
-]
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare read-only, closed-world, idempotent, so the description correctly spends its words elsewhere: it discloses the single-source roster scope, the exact-match normalization rule, and the UNVERIFIED fallback for unknown inputs. It does not cover rate limits or caching, but for a read-only lookup that is minor.

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?

Front-loaded with the core adjudication purpose, then the disambiguation and fallback behavior in tight sentences; nothing is wasted. The telegraphic style ('A SINGLE-SOURCE roster fact') is dense but readable.

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 the return values need not be explained, and the description still covers outcome vocabulary (CONFIRM/DENY/UNVERIFIED) and source scope. The one gap is what happens when claimed_name is omitted, given only deal is required.

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 baseline is 3, and the description goes beyond it: it explains that claimed_name is adjudicated under the ledger's name normalization and never fuzzily, and that role today covers master and special servicer with unknown role yielding UNVERIFIED. It also clarifies that 'master' means the roster party, not the tape's primary servicer, which changes how the role value should be interpreted.

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?

States a precise verb ('Adjudicate') against a named, single-source resource ('SEC 10-D counterparty roster') for a specific question ('who is the <role> on deal X'). It explicitly draws the boundary against the ABS-EE tape's primary servicer, which distinguishes it from the sibling verify_servicer.

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?

Gives clear operating conditions: pass claimed_name to get CONFIRM/DENY, comparison is under the ledger's name normalization and never fuzzy, and unknown deal or role returns UNVERIFIED. It does not name the sibling tool to use for the tape-based servicer question, implying the handoff rather than stating it.

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

All CMD+RVL Receipts 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