Skip to main content
Glama
IBM
by IBM

solve_scheduling_problem

Solve task scheduling problems with dependencies and resource constraints, optimizing for makespan, cost, or lateness.

Instructions

Solve a task scheduling problem with dependencies and resource constraints.

This is a high-level interface for scheduling problems. Use this instead of solve_constraint_model when you have tasks with durations, dependencies, and resource constraints. The solver automatically builds the appropriate CP-SAT model.

Args: tasks: List of Task objects to schedule (id, duration required; dependencies, resources, etc. optional) resources: Optional list of Resource objects with capacity constraints objective: SchedulingObjective enum (MINIMIZE_MAKESPAN, MINIMIZE_COST, or MINIMIZE_LATENESS) max_time_ms: Maximum solver time in milliseconds (default 60000)

Returns: SolveSchedulingProblemResponse containing: - status: Solution status - makespan: Project completion time - schedule: List of task assignments with start/end times - resource_utilization: Resource usage summary - critical_path: Task IDs on critical path - solve_time_ms: Actual solve time - optimality_gap: Gap from best bound - explanation: Human-readable summary

Tips for LLMs: - Extract task durations from natural language (e.g., "takes 2 hours" -> duration: 2) - Parse dependencies carefully (e.g., "A before B" -> B depends on A) - Default resource capacity to system constraints if not specified - If user says "as fast as possible", use minimize_makespan - Check for circular dependencies before solving - If infeasible, check for conflicting deadlines or impossible dependencies

Example (simple project schedule): python response = await solve_scheduling_problem( tasks=[ {"id": "build", "duration": 10, "dependencies": []}, {"id": "test", "duration": 5, "dependencies": ["build"]}, {"id": "deploy", "duration": 3, "dependencies": ["test"]} ], objective="minimize_makespan" ) # Returns optimal schedule with makespan = 18

Example (with resource constraints): python response = await solve_scheduling_problem( tasks=[ {"id": "task_a", "duration": 5, "resources_required": {"cpu": 2}}, {"id": "task_b", "duration": 3, "resources_required": {"cpu": 3}}, ], resources=[{"id": "cpu", "capacity": 4}], objective="minimize_makespan" ) # Returns schedule respecting CPU capacity

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tasksYes
objectiveNominimize_makespan
resourcesNo
max_time_msNo
Behavior5/5

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

No annotations provided, but the description fully explains behavior: automatically builds CP-SAT model, returns detailed response with status, makespan, schedule, resource utilization, critical path, solve time, optimality gap, and human-readable explanation. Warns about infeasibility and circular dependencies.

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?

Description is fairly long but well-structured with sections for description, arguments, returns, tips, and examples. Every part adds value, but there is some redundancy (e.g., duplicate explanations in text and examples). Could be slightly more concise.

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 4 parameters and no output schema, the description is comprehensive: explains input structure, returns, tips for LLMs, and includes two examples covering basic and resource-constrained scenarios. Covers error handling and edge cases like circular dependencies.

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 description coverage is 0% per context, so description must compensate. The description does not add much to individual parameter definitions beyond the schema, but it provides extensive usage guidance and examples that show how to use parameters effectively. The tips section adds value for an AI agent.

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 it 'Solve a task scheduling problem with dependencies and resource constraints'. It distinguishes from sibling 'solve_constraint_model' by specifying this is for tasks with durations, dependencies, and resource constraints.

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?

Explicitly states 'Use this instead of solve_constraint_model when you have tasks with durations, dependencies, and resource constraints'. Provides tips for LLMs on extracting task information and checking for circular dependencies. Examples illustrate typical use cases.

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/IBM/chuk-mcp-solver'

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