Skip to main content
Glama

run_decision_pipeline

Run a multi-stage decision pipeline that combines counterfactual analysis, scenario generation, and foresight planning to evaluate high-stakes objectives and deliver ranked recommendations with evidence.

Instructions

Run a multi-stage decision pipeline with configurable reasoning stages.

Orchestrates counterfactual reasoning, scenario generation, foresight planning, meta-reasoning, uncertainty estimation, and information-need detection into a single pipeline run. The pipeline evaluates the provided objective and returns a ranked recommendation with evidence.

Use this for high-stakes decisions where multiple perspectives add value. For simpler individual analyses, use the standalone tools (evaluate_plan, generate_scenarios, etc.) instead.

Side effects: Records decision events; if execute_mode='queued_runtime', may enqueue follow-up tasks for runtime execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum events to process (default 10000).
objectiveYesThe decision objective dict describing what to decide.
max_horizonNoMax planning depth (default 5).
execute_modeNo'event_only' (record only), 'queued_runtime' (queue tasks), 'simulate', or 'validate' (default 'event_only').event_only
risk_thresholdNoMaximum acceptable risk score 0-1 (default 0.7).
foresight_limitNoMax action chains per branch (default 5).
scenarios_limitNoMax scenarios to generate (default 4).
enable_foresightNoRun foresight planning (default False).
enable_scenariosNoRun scenario generation (default False).
regret_thresholdNoRegret threshold 0-1 for counterfactual filtering (default 0.2).
enable_uncertaintyNoEstimate epistemic/aleatoric uncertainty (default False).
counterfactual_limitNoMax alternative outcomes to generate (default 3).
enable_counterfactualNoRun counterfactual what-if analysis (default False).
enable_meta_reasoningNoApply meta-reasoning over results (default False).
simulate_before_executeNoSimulate effects before committing (default False).
enable_information_seekingNoIdentify information gaps (default False).
scenario_recommendation_thresholdNoMin score 0-1 for scenario inclusion (default 0.5).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

Discloses side effects (recording events, enqueuing tasks) and that it returns a ranked recommendation with evidence. With no annotations, the description carries full burden and addresses key behaviors, though could mention failure modes.

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 three short paragraphs, each with a distinct purpose (what it does, when to use, side effects). Every sentence adds value, and it is front-loaded with the core function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (17 params, nested objects, output schema exists), the description provides a good overview. It explains the purpose, usage, and side effects. It does not elaborate on return values beyond 'ranked recommendation with evidence', but the output schema should cover details. A 5 would require more on error handling or performance.

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%, baseline 3. The description adds value by explaining that the boolean parameters correspond to specific reasoning stages, which is not fully captured in the schema descriptions. This elevates it above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it runs a multi-stage decision pipeline for high-stakes decisions, listing the reasoning stages. It distinguishes from standalone tools but does not directly compare to the listed siblings, hence not a 5.

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?

Explicitly says to use for high-stakes decisions and to use standalone tools for simpler analyses. While it doesn't name exact siblings, it provides clear guidance on when to use this tool versus alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Mustafa-Ali-Ertugrul/allbrain-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server