Risk Desk

risk_frtb_backtest

Read-onlyIdempotent

FRTB VaR backtesting exception counts at 97.5% and 99%, desk verdict or bank zone (MAR32). Omit the request to run the shipped synthetic example instead. For supplied data, require permission and set rights_confirmed=true; this does not verify a licence.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "risk_frtb_backtest"
  }
}

Input Schema

Name	Required	Description	Default
`request`	No
`rights_confirmed`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Beyond the read-only, idempotent, and non-destructive annotations, it discloses the no-request synthetic fallback and the permission requirement for user data, including that rights_confirmed does not verify a licence. It adds little about validation or computational behavior, such as null handling or what happens when var_975 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.

Conciseness5/5

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

Three compact sentences front-load the regulatory purpose, then cover default execution and data-rights behavior. The MAR32 reference and licensing caveat are dense but functional, with no redundant restatement of schema constraints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Together with the structured input and output schemas, the description is sufficient to select the tool and confidently run its synthetic example. For licensed-data invocation, however, the undefined request fields and missing explanation of the required and optional VaR series leave significant gaps, while sibling-routing guidance is also absent.

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

Parameters2/5

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

With 0% schema description coverage, the description usefully explains request omission and rights_confirmed, and indirectly distinguishes synthetic from supplied-data operation. However, it does not define APL/HPL, source and as_of expectations, alignment or null semantics for the 250-item series, or the effect of omitting var_975, leaving most real-data parameter semantics to inference.

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 identifies FRTB VaR backtesting, exception counts at 97.5% and 99%, and desk-versus-bank results under MAR32. This clearly conveys the regulatory calculation and outputs, although it does not explicitly differentiate the tool from risk_backtest or other FRTB siblings.

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?

It gives concrete guidance for both modes: omit request to run the shipped synthetic example, and obtain permission before setting rights_confirmed=true for supplied data. It does not explain when this MAR32 backtest is preferable to a generic backtest or when it should not be used.

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

All Risk Desk 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.