Optimization Solver (LP / MIP Scheduling)

Optimization Solver — Get Engine Script (large models)

optimization_solver_get_engine

Read-only

For models above ~3,000 variables or constraints, long runs (time limit over 60 s), MPS files, or any table already in your code sandbox. Returns a complete numpy-only Python script with the same engine as optimization_solver; it reads the tables (CSV / TSV / JSON) or MPS file named in the call, prints the decision cards and the plan summary, and writes the full result to optimization_result.json. No data reaches this server on this path.

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": "optimization_solver_get_engine"
  }
}

Input Schema

Name	Required	Description
`params`	No	Other inputs exactly as optimization_solver takes them (problem_type, budget, batch_size, time_limit_seconds up to 600 ...).
`mps_path`	No	MPS model file in your sandbox.
`jobs_path`	No	jobs file in your sandbox (CSV/TSV/JSON).
`costs_path`	No	costs file in your sandbox (CSV/TSV/JSON).
`staff_path`	No	staff file in your sandbox (CSV/TSV/JSON).
`usage_path`	No	usage file in your sandbox (CSV/TSV/JSON).
`groups_path`	No	groups file in your sandbox (CSV/TSV/JSON).
`shifts_path`	No	shifts file in your sandbox (CSV/TSV/JSON).
`budgets_path`	No	budgets file in your sandbox (CSV/TSV/JSON).
`periods_path`	No	periods file in your sandbox (CSV/TSV/JSON).
`sources_path`	No	sources file in your sandbox (CSV/TSV/JSON).
`machines_path`	No	machines file in your sandbox (CSV/TSV/JSON).
`products_path`	No	products file in your sandbox (CSV/TSV/JSON).
`projects_path`	No	projects file in your sandbox (CSV/TSV/JSON).
`resources_path`	No	resources file in your sandbox (CSV/TSV/JSON).
`variables_path`	No	variables file in your sandbox (CSV/TSV/JSON).
`constraints_path`	No	constraints file in your sandbox (CSV/TSV/JSON).
`ingredients_path`	No	ingredients file in your sandbox (CSV/TSV/JSON).
`current_plan_path`	No	current_plan file in your sandbox (CSV/TSV/JSON).
`destinations_path`	No	destinations file in your sandbox (CSV/TSV/JSON).
`requirements_path`	No	requirements file in your sandbox (CSV/TSV/JSON).

Output Schema

Name	Required	Description	Default
`notes`	No
`paths`	No
`script`	Yes
`language`	No
`requires`	No
`writes_file`	No
`instructions`	Yes
`engine_version`	Yes
`scipy_required`	No
`data_requirements`	No
`network_access_required`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare read-only, non-destructive, open-world. The description adds important context: no data reaches the server, the returned script writes results to optimization_result.json, and it prints decision cards and plan summary. It does not detail execution permissions or whether the script runs automatically.

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?

Three sentences, front-loaded with usage conditions, then output and privacy. No redundant or vague phrasing; every sentence contributes.

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 21-parameter tool with nested params and an output schema, the description covers when to use it, what it returns, side effects, and privacy. The schema handles individual path details, so nothing critical is 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% with descriptions for all 21 path parameters. The description restates file formats and that params mirror optimization_solver, but adds no new syntax or constraints beyond what the schema already provides.

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 states a specific action (returns a complete numpy-only Python script) and resource (engine script for large models), and distinguishes from the sibling by noting it uses the same engine as optimization_solver for larger/sandbox scenarios.

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?

It lists explicit conditions for use: models above ~3,000 variables/constraints, long runs (time limit over 60 s), MPS files, or tables already in the sandbox. It implies optimization_solver is the alternative for smaller/online cases but does not name it as an explicit fallback.

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

All Optimization Solver (LP / MIP Scheduling) tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.