Skip to main content
Glama
thyn-ai

Algenta MCP

Official
by thyn-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

product_decision

Read-onlyIdempotent

Turn plain business inputs into a recommended decision: proceed, pause, or reject, backed by a risk summary with confidence and loss probability.

Instructions

Recommend an action for a business decision from plain inputs, and return the risk summary behind it. Each input becomes a simulation variable: fixed at value, or triangular when low and high bounds are given; inputs named cost/costs/expense/expenses/spending are subtracted in the objective. The engine evaluates scenarios (default 10000) and maps the loss probability to an action: over 50% -> reject, over the risk_tolerance threshold (low 5%, medium 15%, high 30%) -> pause, otherwise proceed. Use simulate for the raw distribution and plan_decision for the structured plan. Synchronous deterministic compute; nothing is persisted. Returns decision_id, action, confidence, reasoning and why bullets, expected_outcome, downside_risk (p5), upside_potential (p95), and probability_of_loss.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
labelNoOptional caller label stored with the decision.
engineNoSimulation engine; auto (default) selects one from the data shape. Options: monte_carlo, lhs, qmc_sobol, bootstrap, mcmc, importance_sampling, time_series, sensitivity.
inputsYesBusiness inputs as {name, value, low?, high?, unit?} objects; low+high turn a value into a triangular uncertainty range.
objectiveNoGoal label such as maximize_value, minimize_risk, maximize_profit, or minimize_cost; defaults to maximize_value.
scenariosNoScenarios to evaluate, 1000-1000000; defaults to 10000.
risk_toleranceNoLoss-probability ceiling for a proceed recommendation: low, medium (default), or high.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.1.3
    • addedInput schema / properties / engine / description
      Added value: +"Simulation engine; auto (default) selects one from the data shape. Options: monte_carlo, lhs, qmc_sobol, bootstrap, mcmc, importance_sampling, time_series, sensitivity."
    • changedInput schema / properties / inputs / description
      Previous value: -"Business inputs with current value and optional low/high bounds."New value: +"Business inputs as {name, value, low?, high?, unit?} objects; low+high turn a value into a triangular uncertainty range."
    • addedInput schema / properties / label / description
      Added value: +"Optional caller label stored with the decision."
    • addedInput schema / properties / objective / description
      Added value: +"Goal label such as maximize_value, minimize_risk, maximize_profit, or minimize_cost; defaults to maximize_value."
    • addedInput schema / properties / risk_tolerance / description
      Added value: +"Loss-probability ceiling for a proceed recommendation: low, medium (default), or high."
    • addedInput schema / properties / scenarios / description
      Added value: +"Scenarios to evaluate, 1000-1000000; defaults to 10000."
  2. First observedv0.1.0

TDQS

A5/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description adds substantial behavioral context: it explains the simulation algorithm, how inputs are converted to variables, cost handling, threshold mapping, determinism ('Synchronous deterministic compute'), and that nothing is persisted. This is far more than minimal disclosure and fully aligns with annotations.

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?

The description is a single dense paragraph that is well-organized: purpose first, then mechanics, then sibling differentiation, then behavior, then return fields. Every sentence earns its place, and it avoids redundancy. Despite its length, it remains clear and scannable.

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 (6 parameters, no output schema), the description is remarkably complete. It explains the full decision algorithm, the exact return fields (decision_id, action, confidence, reasoning, etc.), the threshold logic, and the persistence behavior. An agent has everything needed to invoke it correctly and interpret results.

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

Parameters5/5

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

Schema coverage is 100%, but the description goes well beyond the schema by explaining how each parameter affects behavior: inputs become simulation variables with triangular uncertainty, cost-named inputs are subtracted, scenarios defaults to 10000, risk_tolerance maps to specific thresholds (low 5%, medium 15%, high 30%), and objective influences the loss calculation. This adds critical meaning that the schema alone does not convey.

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 clearly states the tool's purpose: 'Recommend an action for a business decision from plain inputs, and return the risk summary behind it.' It uses a specific verb (recommend) and resource (business decision), and explicitly distinguishes itself from siblings by naming simulate and plan_decision as alternatives for different needs.

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 guidance on when to use this tool versus alternatives: 'Use simulate for the raw distribution and plan_decision for the structured plan.' This tells the agent exactly which sibling to choose for other use cases, leaving no ambiguity.

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

Deploy Server

Other Tools