brazil-macro-ai

brazil_monetary_policy_divergence

Assess divergence between Brazilian market-implied monetary policy, economist expectations, inflation breakevens and realized inflation surprises, using point-in-time public data with full provenance (method_id monetary_policy_divergence_v1).

Consumes ONLY the already-homologated capability layer (market-vs-Focus
meeting gaps, Focus Selic/IPCA 4-week revisions, the 5Y inflation
breakeven and its 20-business-day change, and the latest eligible IPCA
surprise) — never recomputes those engines and never fabricates a
number a component doesn't support. Each of the 5 evidence components
gets its own deterministic classification (strong_dovish..strong_
hawkish) with a versioned threshold set (threshold_version
B4_THRESHOLDS_V1), quality-weighted by the underlying engine's own
quality_status. `overall_signal` is a QUALITATIVE composite
(strong_dovish/dovish/balanced/hawkish/strong_hawkish/
insufficient_evidence) — deliberately NOT a fabricated 0-100 score.
`evidence_agreement` (0-1) tells you separately whether the components
agree with each other, independent of the direction of the signal.

IMPORTANT: `product_validation_status` is "internal_validated_external_
pending" until C0's external benchmark passes (see
docs/C0_external_validation_protocol.md), then "validated" — several
inputs (the market-implied Copom path, the real/breakeven curve) are
themselves still individually pending external benchmark validation,
never hidden here. This is macro intelligence, NOT an investment
recommendation.

Use when: assessing whether Brazilian market pricing, economist
consensus, market-implied inflation and realized inflation data agree
or diverge on the direction of monetary policy pressure.
Do not use when: you need only one dimension — use
compare_brazil_market_vs_focus, brazil_focus_revisions,
brazil_inflation_breakeven, or brazil_macro_surprise directly.

Args:
    as_of: optional YYYY-MM-DD date. Defaults to today.
    horizon_meetings: must be 4 in v1 (the PolicyGap weighting
        0.40/0.30/0.20/0.10 is fixed for exactly 4 meetings).
    include_evidence: if true (default), include the full per-component
        evidence table (value, signal, quality_status, weights,
        validation status, source vintage).
    payment_token: required in staging ($0.25/call per pricing.yaml).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`as_of`	No
`agent_id`	No
`session_id`	No
`payment_token`	No
`discovery_source`	No
`horizon_meetings`	No
`include_evidence`	No
`synthetic_identity`	No

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?

With no annotations provided, the description carries the full burden, and it is thorough: it discloses that the tool never recomputes underlying engines, never fabricates unsupported numbers, uses deterministic classifications with versioned thresholds, reports validation status including external-pending states, and is explicitly not an investment recommendation. It also mentions the payment token requirement and per-call pricing in staging.

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 long but well-structured: purpose is front-loaded, followed by methodology, caveats, usage guidance, and arguments. Some method detail is dense, but it earns its place given the analytical complexity and the absence of annotations or schema descriptions.

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?

For a complex analytical tool with an output schema present, the description covers purpose, methodology, data provenance, validation caveats, compositing logic, parameter constraints, and alternatives. It is sufficiently complete for an agent to invoke the tool correctly and interpret its qualitative signal without additional external context.

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 0%, so the description must compensate. It adds useful meaning for as_of, horizon_meetings, include_evidence, and payment_token, including the fixed 4-meeting constraint and the default evidence table contents. However, it omits four schema parameters (agent_id, session_id, discovery_source, synthetic_identity), leaving them entirely unexplained.

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 specific verb and resource: 'Assess divergence between Brazilian market-implied monetary policy, economist expectations, inflation breakevens and realized inflation surprises.' It clearly distinguishes itself from siblings by name in the 'Do not use when' section, so an agent can tell it apart from tools like compare_brazil_market_vs_focus or brazil_focus_revisions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit 'Use when' and 'Do not use when' guidance, naming concrete sibling alternatives for single-dimension needs. It also specifies that the tool consumes only the already-homologated capability layer and should not be called when only one dimension is required.

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

All brazil-macro-ai 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?