Skip to main content
Glama

crashtestyourstrategy

Regime-probability outlook (validated assets, h=5/21)

regime_outlook
Read-onlyIdempotent

USE WHEN you want the probability that SPY, QQQ, GLD or TLT is in each market regime on trading day 5 or 21. Model-conditional probabilities of BULL / SIDEWAYS / BEAR / CRISIS (operational trailing-vol/drift labels) on trading day 5 or 21, not at any point before it: stress tools answer 'what happens GIVEN regime X', this answers 'how likely is X from today's state'. Uses the preregistered covariate logit; persistence and unconditional baselines are reported beside it. On GLD at 21 days it did not beat persistence (p=0.64), so that cell uses persistence, as market_regime_map does; model.tier says which. Assets: SPY, QQQ, GLD, TLT (GOLD accepted for GLD). Optional as_of (YYYY-MM-DD) evaluates a past date. Class membership on a future day, not a forecast of returns or direction, not advisory.

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": "regime_outlook"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNoOptional historical evaluation date (YYYY-MM-DD); empty = latest data.
assetNoOne of the out-of-sample-validated assets: 'SPY', 'QQQ', 'GLD', 'TLT' (GOLD is read as GLD).SPY
horizon_daysNoThe trading day the probabilities refer to, counted from the evaluation date. Validated: 5 or 21.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / horizon_days / description
      Previous value: -"Validated horizons only: 5 or 21 trading days."New value: +"The trading day the probabilities refer to, counted from the evaluation date. Validated: 5 or 21."
  2. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / asset / description
      Previous value: -"One of the out-of-sample-validated assets: 'SPY', 'QQQ', 'GLD', 'TLT'."New value: +"One of the out-of-sample-validated assets: 'SPY', 'QQQ', 'GLD', 'TLT' (GOLD is read as GLD)."
  3. Changed3 schema fields changed
    • addedInput schema / properties / as_of / description
      Added value: +"Optional historical evaluation date (YYYY-MM-DD); empty = latest data."
    • addedInput schema / properties / asset / description
      Added value: +"One of the out-of-sample-validated assets: 'SPY', 'QQQ', 'GLD', 'TLT'."
    • addedInput schema / properties / horizon_days / description
      Added value: +"Validated horizons only: 5 or 21 trading days."
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/closed-world, and the description adds real depth beyond them: model-conditional construction, reported persistence and unconditional baselines, a documented model failure at GLD/21 (p=0.64) with a persistence fallback flagged by model.tier, and historical evaluation via as_of. The only shortfall is that it doesn't say what else the response contains or how confidence should be read, though an output schema exists.

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 USE WHEN and free of filler, but the middle sentences are dense and cram statistical caveats (baselines, p-value, fallback tier) into long clauses that could be split. Every sentence carries information; readability, not waste, is the weak point.

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?

Covers assets, horizons, historical evaluation, statistical caveats and the persistence fallback, and an output schema handles return values. For a probabilistic read-only tool, nothing an agent needs to invoke it correctly appears missing.

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 coverage is 100%, and the input schema already documents as_of, asset (including the GOLD alias) and horizon_days (validated 5 or 21). The description restates these without adding format or constraint detail beyond the schema, so the baseline 3 applies.

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?

Opens with a specific verb and resource: the probability that SPY, QQQ, GLD or TLT is in each regime on trading day 5 or 21. It explicitly contrasts itself with stress tools ('what happens GIVEN regime X' vs 'how likely is X from today's state'), so an agent can separate it from run_stress_test and long_horizon_stress without opening schemas.

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 USE WHEN clause names the exact question and the acceptable assets and horizons, and explicitly sets the exclusion boundary against stress tools. It also names the fallback sibling (market_regime_map) for the persistence-based GLD 21-day cell, giving the agent a concrete alternative path.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.