BrunoSan AI News Intelligence

news_risk_radar

Read-onlyIdempotent

Active risk and compliance signals ranked by combined_risk_score: combined_risk_score = (risk_signal_count * 2) + (compliance_signal_count * 3) + (official_source_count * 1)

Open formula. Auditable. The AI News equivalent of the Regulatory MCP's
reg_score — covering all AI news, not just regulatory documents.

Example queries:
    - "What AI risk and compliance signals are active today?"
    - "Show all clusters with compliance_signals above 2 — what's legally relevant in AI right now?"
    - "Daily risk scan for our AI governance team — top 5 clusters by combined_risk_score, with source breakdown and official source count"
    - "Which AI risk signals came from official sources like governments or regulators? Filter official_sources > 0, rank by compliance signal density"
    - "Map today's risk radar against last week's — which new risk clusters appeared? Which escalated? Delta report for weekly risk committee"

Args:
    params (RiskRadarInput):
        - date: YYYY-MM-DD, empty for latest
        - min_official_sources: filter to clusters with at least N official sources
        - min_compliance_signals: filter to clusters with at least N compliance signals
        - limit: number of clusters to return

Returns:
    str: JSON with date, formula, filters_applied, count, and clusters
    list (each with combined_risk_score and the three component counts).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds context beyond them: it discloses the calculation, states that the formula is open and auditable, and specifies the returned JSON fields including date, formula, filters_applied, count, and clusters. For a read-only ranked report, this is strong behavioral disclosure.

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 description is front-loaded with the core purpose and formula, then organized into Args, Returns, and examples. The five example queries are useful for an agent deciding how to phrase inputs, though somewhat repetitive. Overall, it is structured and readable without significant waste.

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?

Given the tool's complexity—five parameters, a nested input object, a scoring formula, and a structured response—the description covers the logic, filter behavior, response shape, and representative use cases. Nothing critical is missing for an agent to select and invoke it correctly; authentication is handled by the api_key parameter in the schema.

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?

Although the schema already documents each parameter, the description clarifies their semantic role by linking min_official_sources and min_compliance_signals to the formula components and by demonstrating usage through example queries. It also clarifies that an empty date means the latest available day and that the response includes component counts. This adds meaning beyond the raw schema.

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?

The description opens with a precise statement—'Active risk and compliance signals ranked by combined_risk_score'—and exposes the exact scoring formula. This clearly distinguishes it from generic news search tools by anchoring on risk/compliance aggregation and ranked output. The explicit formula removes ambiguity about what the tool computes.

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 provides concrete use scenarios (daily risk scan, delta report for weekly risk committee, compliance-signal filtering) and positions the tool as the AI-news equivalent of the Regulatory MCP's reg_score, covering all AI news rather than regulatory documents. However, it does not explicitly name alternative sibling tools or state when not to use this tool, so it stops short of full exclusionary guidance.

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

All BrunoSan AI News Intelligence 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.

Resources

Need Help?