Skip to main content
Glama
thyn-ai

Algenta

Official
by thyn-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

product_decision

Read-onlyIdempotent

Recommend a proceed, pause, or reject action for a business decision from plain inputs, returning a risk summary with confidence, downside, and upside potential.

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. Which to use: a proceed/pause/reject answer from plain business inputs; use simulate for full distribution control and the envelope.

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

A4.9/5.0
Behavior5/5

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

The description adds behavior beyond the annotations: it states the computation is 'Synchronous deterministic compute; nothing is persisted,' explains how cost-named inputs are subtracted, and documents the exact reject/pause/proceed thresholds. It complements the readOnly and idempotent hints without contradicting them.

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 dense but organized, covering purpose, input interpretation, action mapping, return fields, and sibling routing in a compact block. Every clause carries decision-relevant information, and the final 'Which to use' sentence reinforces the selection rule without unnecessary repetition.

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?

There is no output schema, and the description compensates by explicitly listing all returned fields: decision_id, action, confidence, reasoning, expected_outcome, downside_risk, upside_potential, and probability_of_loss. It also covers persistence behavior, default scenarios, thresholds, and sibling alternatives, making the tool fully callable from the description alone.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantics: low/high bounds create triangular uncertainty, cost-named inputs affect the objective, and risk_tolerance thresholds map to specific action cutoffs. The schema documents shapes and defaults; the description explains behavioral interpretation of those parameters.

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-resource pair: 'Recommend an action for a business decision from plain inputs, and return the risk summary behind it.' It also explicitly distinguishes this tool from sibling tools 'simulate' and 'plan_decision', making the purpose and boundary clear.

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 gives explicit routing guidance: 'Use simulate for the raw distribution and plan_decision for the structured plan' and ends with 'Which to use: a proceed/pause/reject answer from plain business inputs; use simulate for full distribution control and the envelope.' This tells the agent when to choose this tool and when to pick an alternative.

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