Abs Loan Level

Abs Asset Lookup

abs_asset_lookup

Read-onlyIdempotent

Look up ONE loan or lease in an ABS-EE asset-level disclosure filing by accession number and asset number: original loan amount, term, rate, origination and maturity dates, vehicle, period-end balance, delinquency days, zero-balance code and the full set of disclosed fields for that reporting period. Reads SEC EDGAR asset-data exhibits (Regulation AB II) by streaming the exhibit and stopping at the match; a very large exhibit can take up to about a minute. An asset number that is not in the exhibit returns reason asset_not_found only after the whole exhibit was read; an interrupted read returns scan_incomplete, never a false not-found.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "accession": "0002057342-26-000037",
      "asset_number": "018050022666"
    },
    "name": "abs_asset_lookup"
  }
}

Input Schema

Name	Required	Description
`cik`	No	Optional filer CIK the filing sits under, when it differs from the accession prefix.
`accession`	Yes	ABS-EE filing accession number, e.g. "0002057342-26-000037".
`asset_number`	Yes	The assetNumber as disclosed, e.g. "018050022666".

Output Schema

Name	Required	Description
`found`	No	Whether the asset was found
`notes`	No
`fields`	No	Every disclosed field of the asset row; repeated tags are arrays
`reason`	No	filing_not_found, no_asset_data_exhibit, scan_incomplete, asset_not_found
`source`	No	Publisher and dataset
`message`	No	Explanation when found is false
`summary`	No	Key fields of the asset row (amounts in USD, percentages as decimal fractions, delinquency in days)
`accession`	No	Filing accession number
`asset_number`	No	Asset number as disclosed
`exhibits_scanned`	No	Exhibits read
`reporting_period`	No	Reporting period
`exhibit_bytes_scanned`	No	Bytes of the exhibit read

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 14, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses the streaming read strategy, an expected latency ceiling of about a minute for very large exhibits, and precise error semantics (asset_not_found only after the full exhibit is read; scan_incomplete on interrupted read, never a false not-found). Annotations already cover safety/idempotency, so this adds genuinely new operational context.

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 action and keys, followed by latency and error behavior, with no filler sentences. The long field enumeration in the first sentence is dense but earns its place by telling the agent what data comes back without opening the output schema.

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?

An output schema exists so return values need no explanation, and the description still covers scope (single asset), input keys, runtime expectations, and failure modes. For a read-only lookup of this complexity, an agent has everything needed to call it correctly and interpret a failure.

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%, so all three parameters (including the optional cik override) are already documented in the schema. The description reinforces that lookup is keyed on accession plus asset number 'as disclosed' but adds no syntax, format, or edge-case detail beyond the schema — baseline 3 is appropriate.

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 specific verb and resource — 'Look up ONE loan or lease in an ABS-EE asset-level disclosure filing by accession number and asset number' — and enumerates the disclosed fields returned (original amount, term, rate, dates, vehicle, balance, delinquency, zero-balance code). The capitalized 'ONE' makes it distinguishable at a glance from the aggregate siblings like abs_trust_performance and abs_sector_delinquency.

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?

The emphasis on 'ONE' asset implicitly routes the agent away from portfolio/sector-level tools, and the required accession + asset number make the precondition explicit. It does not explicitly name a sibling tool or state when-not-to-use, so it stops short of a 5.

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

All Abs Loan Level 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.