Moltline Optimize

Route Plan Fleet

route_plan_fleet

Read-onlyIdempotent

Capacitated, time-windowed routing for a fleet over up to 200 stops. PREMIUM (license).

Typical input {"stops": [{"id": "depot", "window": [480, 1080]}, {"id": "A", "demand": 3, "window": [540, 720], "service_min": 10}, ...], "matrix": [[...]], "vehicles": [{"id": "van1", "capacity": 10}, {"id": "van2", "capacity": 8, "max_distance": 120}]} returns {"routes": [{"vehicle": "van1", "stops": [{"id": "A", "arrive_min": 545, ...}], "distance": 42.5, "load": 9}], "unserved": [], "solver_status": "FEASIBLE"}. Windows and service times are minutes from the start of the day; travel time comes from time_matrix (minutes) or, if absent, the distance matrix read as minutes. Set drop_penalty to allow stops to be left unserved at that cost instead of returning INFEASIBLE. Use for daily dispatch. Not a map service; bring your own matrices. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "stops must be a list of stop objects, depot first"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input Schema

TableJSON Schema

Name	Required	Description
`depot`	No	index of the depot in stops (default 0).
`stops`	Yes	depot first; each: id, demand, window [earliest_min, latest_min], service_min.
`matrix`	Yes	square distance matrix in your units.
`vehicles`	Yes	list of {id, capacity, max_distance}; capacity in the units of demand.
`time_matrix`	No	optional square travel-time matrix in minutes (defaults to matrix).
`drop_penalty`	No	cost of leaving a stop unserved (0 = every stop must be served).
`time_limit_s`	No	solver time budget in seconds (default 10, max 60).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the annotations, it discloses that invalid input never raises a protocol error but returns an error object, that unsterved stops are listed, that zero-demand stops are always dropped, that units are minutes and demand units, and that calls are safe to retry. These behavior details go well beyond readOnlyHint/idempotentHint and add real value.

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?

The description is well-structured and front-loaded, with purpose, example, units, usage guidance, and edge cases in logical order. It is slightly longer than necessary because it restates read-only/idempotent behavior already present in annotations and contains a self-correcting zero-demand edge case, but it is not bloated.

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 7-parameter solver with an output schema, the description covers purpose, I/O shape, units, defaults, error protocol, edge cases, and sibling routing. An agent has everything needed to decide whether to call it, construct input, interpret output, and recover from failures.

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?

Although schema coverage is 100%, the description adds substantive meaning: windows and service times are minutes from the start of the day, travel time comes from the matrix, returned loads are in demand units, max_distance absent means unlimited, and window [0, 1440] means anytime. The worked input/output example maps parameter names to concrete values.

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 opening sentence names a specific operation: 'Capacitated, time-windowed routing for a fleet over up to 200 stobs.' It later clarifies scope ('This tool only otimizes the routes for a fixed fleet') and explicitly distinguishable from route_plan and pack_bins, so an agent can tell it apart from siblings without opening the schema.

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?

It gives explicit when-to-use guidance: use pack_bins or pack_bins_large to build a fleet, use route_plan for a single uncapacitated route, use validate_problem for solver errors, and use explain_solution to explain output. This is model guidance on alternatives and conditions.

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

All Moltline Optimize tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0

Disambiguation5/5

Each solver targets a distinct optimization domain (cutting, packing, routing, knapsack, rostering), and scale variants like pack_bins/pack_bins_large and route_plan/route_plan_fleet are explicitly differentiated by size/scope. Helper and meta tools (distance_matrix_haversine, validate_problem, explain_solution) are clearly separate from solve tools.

Naming Consistency4/5

Names are uniformly lowercase snake_case and organized into recognizable families such as cutting_stock_1d/2d, pack_bins/pack_bins_large, and route_plan/route_plan_fleet. The pattern is not strictly verb_object throughout—knapsack_select and distance_matrix_haversine are noun-first or descriptive—so there is minor inconsistency.

Tool Count5/5

With 11 tools, the server is well-scoped for an optimization toolkit: one core solver per problem type, a large-scale packer variant, a distance-matrix helper, and validation/explanation tools. Each tool has a clear role, and the count supports broad coverage without becoming bloated.

Completeness4/5

The server covers a complete solve-validate-explain workflow across major OR problem types—cutting, packing, routing, knapsack, and rostering. Minor gaps exist, such as pack_bins_large not being listed as recognized by explain_solution, and some features are explicitly documented exclusions rather than missing functionality.

Resources

Need Help?