Skip to main content
Glama

optimise_routes

Optimise multi-vehicle, multi-stop delivery plans (VRP). Provide vehicles (id, start/end, capacity, skills, time_window), jobs (id, location, service_s, delivery/pickup, skills, time_windows) and/or shipments (pickup+delivery pairs that ride the same vehicle). Costing "auto", "truck", "bicycle", "pedestrian" or "motor_scooter" (cargo-bike and courier fleets welcome): with a truck profile (dimensions + ADR declaration, as in route), the travel-time matrix respects dimensional and dangerous-goods restrictions, so every optimised route is truck-legal. Returns a summary, unassigned tasks and per-vehicle routes with ordered steps (arrival_s/duration_s in seconds, distance_m in metres). Fair use: at most 200 unique locations per problem, and no wider than the routing engine's 400 km matrix span — past that, cluster the stops with cluster and optimise each group, or submit the whole problem to the asynchronous lane with submit_optimise_job (2,000 locations). Optional territories are named polygons ([{id, polygon}], GeoJSON [lon, lat] rings, LONGITUDE FIRST) that bound who serves what: a vehicle listing territory_ids may serve a task only if that task sits inside at least one of the territories it names, while a vehicle listing none is unrestricted and may serve anything, inside a round or outside every one. The response's territories block says which vehicle was eligible for what and names any task no vehicle could take. A vehicle may also declare reloads {max_trips 2-5, reload_time_s, depot?} to return to a depot, reload and go out again — the tipping round. It needs a time_window, because the shift is what gets split: it is cut into that many consecutive non-overlapping windows separated by the reload time, each trip carrying the vehicle's FULL capacity and task caps. That split is fixed BEFORE the solve, so the plan is conservative and never optimistic — it cannot put a lorry in two places at once — but it is an approximation: a trip that finishes early cannot lend its spare time to the next, so stops can come back unassigned that a truly sequential model would have served, and max_trips is a budget rather than a prediction (ask for five on a shift that supports three and every window shrinks to a fifth). Read the returned reloads block before quoting arrival times, and re-plan after each tip with replan_routes for the tighter answer. relax_if_unassigned {time_windows_by_s?, allow_overtime_s?} re-solves ONCE with those relaxations if the first plan left work unassigned, and the relaxation block says honestly which plan came back: at most one second solve, never beyond the caps stated, and the relaxed plan is returned ONLY if it assigns more work than the first. Breaks are never widened — a driver's rest is not a preference to trade for a fuller van — and neither are capacities, skills, territories or task caps; only time windows move. It bills as two solves when the second one runs. Always check relaxation.relaxed_plan_used before telling anyone the day fits: a plan produced under relaxation has had promises moved. emissions {vehicle_category, fuel, euro_standard} annotates the plan with the clean-air zones its own stops sit in and what this vehicle pays in each; add avoid_zones: true to steer the travel-time matrix out of them, which changes the plan itself. Territories, reloads, relaxation and zones are computed by the MapMap gateway; without one configured the tool refuses rather than returning a plan that quietly ignored them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
jobsNoSingle-stop jobs (at least one job or shipment overall).
truckNoTruck profile (dimensions + ADR declaration). Requires costing "truck"; the travel-time matrix then respects dimensional and dangerous-goods restrictions, so the whole plan is truck-legal.
costingNoCosting model for the travel-time matrix: "auto" (default), "truck", "bicycle", "pedestrian" or "motor_scooter".auto
vehiclesYesThe fleet (at least one vehicle, each with a start and/or end).
emissionsNoThe fleet's emission declaration, for UK clean-air / low-emission zone assessment. On its own it annotates: the response's `zones` block names every zone containing one of the problem's own locations and what this vehicle would pay there. With `avoid_zones` it also steers the internal travel-time matrix away from those zones, so the plan itself changes.
shipmentsNoPickup+delivery pairs.
avoid_zonesNoKeep the optimisation's travel-time matrix out of every zone the declared vehicle would be charged or banned in. Requires `emissions`.
territoriesNoFleet territories: named polygons that bound which vehicle may serve which stop, referenced by `vehicles[].territory_ids`. These are request data — caller-drawn rounds, validated per call and never stored. Nothing to do with clean-air zones or with the offline map packages of the same word.
relax_if_unassignedNoRe-solve ONCE with these relaxations if the first solve leaves work unassigned, and say honestly which plan came back. At most one second solve, never beyond the caps you state, and the relaxed plan is returned only if it assigns MORE work than the first — giving away constraints for nothing is strictly worse than not giving them away. Breaks are never widened, nor are capacities, skills, territories or task caps: only time windows move, and only by the stated amounts. Bills as two solves when the second one runs.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
zonesNoClean-air / low-emission zones touching the problem's own locations, and what the declared vehicle pays in each. Present only when `emissions` was declared.
routesYesOne optimised route per used vehicle.
profileYesThe matrix costing profile the plan was computed with ("auto", "truck", "bicycle", "pedestrian" or "motor_scooter").
reloadsNoThe multi-trip split: each vehicle's trips, their windows, the depot each returns to, and the stated approximation. Present only when a vehicle declared `reloads`. Read the `basis` inside it before quoting arrival times. The trip windows are fixed BEFORE the solve, so a lorry that tips early cannot lend the spare time to its next trip: stops can come back unassigned that a truly sequential model would have served. The plan is feasible, never optimistic — it cannot put a vehicle in two places at once — but it is not optimal. Re-plan after each tip through `replan_routes` for the tighter answer.
summaryYesSolution summary.
relaxationNoThe relaxation report: the caps requested, whether a second solve ran, whether ITS plan is the one returned, what was widened, and what is still unassigned. Present only when `relax_if_unassigned` was declared. Always read `second_solve` and `relaxed_plan_used` before telling anyone the day fits. A plan produced under relaxation has had promises moved, and the block is what says so.
unassignedYesTasks the solver could not assign to any vehicle.
territoriesNoHow the territories bound the plan: which vehicle was eligible for what, and any task no eligible vehicle existed for. Present only when `territories` was declared.

Schema Changelog

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

  1. Changed16 schema fields changed
    • addedInput schema / $defs / EmissionsFuel
      Added value: +{
      +  "description": "What a vehicle burns, in clean-air-zone scheme terms.",
      +  "oneOf": [
      +    {
      +      "const": "petrol",
      +      "description": "Petrol, including petrol hybrids (schemes rate a hybrid by its\ncombustion engine's approval).",
      +      "type": "string"
      +    },
      +    {
      +      "const": "diesel",
      +      "description": "Diesel, including diesel hybrids.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "electric",
      +      "description": "Battery-electric.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "hydrogen",
      +      "description": "Hydrogen fuel cell.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "gas",
      +      "description": "LPG or CNG; rated as petrol by every scheme in the dataset.",
      +      "type": "string"
      +    }
      +  ]
      +}
    • addedInput schema / $defs / EmissionsSpec
      Added value: +{
      +  "description": "A vehicle's emission declaration, for clean-air / low-emission zone\nassessment.",
      +  "properties": {
      +    "euro_standard": {
      +      "description": "Its Euro emission standard, 1–6. Heavy-duty approvals are written\nin Roman numerals (Euro VI); declare Euro VI as `6`. Required for\nany combustion fuel — without it no zone can be resolved, and a\nhalf-declared vehicle is indistinguishable from an undeclared one.\nOptional only for `electric` or `hydrogen`.",
      +      "format": "uint8",
      +      "maximum": 255,
      +      "minimum": 0,
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    },
      +    "fuel": {
      +      "$ref": "#/$defs/EmissionsFuel",
      +      "description": "What it burns."
      +    },
      +    "vehicle_category": {
      +      "$ref": "#/$defs/EmissionsVehicleCategory",
      +      "description": "What kind of vehicle this is, in scheme terms."
      +    }
      +  },
      +  "required": [
      +    "vehicle_category",
      +    "fuel"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / $defs / EmissionsVehicleCategory
      Added value: +{
      +  "description": "What a vehicle is, in clean-air-zone scheme terms.\n\nDeclaring this turns \"charge depends on vehicle emissions\" into an\nanswer. Without it a zone can only be named, never priced.",
      +  "oneOf": [
      +    {
      +      "const": "car",
      +      "description": "A private car.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "van",
      +      "description": "A van or light goods vehicle up to 3.5 tonnes.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "minibus",
      +      "description": "A minibus (typically 8+ passenger seats, up to 5 tonnes).",
      +      "type": "string"
      +    },
      +    {
      +      "const": "hgv",
      +      "description": "A heavy goods vehicle over 3.5 tonnes.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "bus",
      +      "description": "A bus over 5 tonnes.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "coach",
      +      "description": "A coach over 5 tonnes.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "taxi",
      +      "description": "A licensed hackney carriage.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "phv",
      +      "description": "A private hire vehicle.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "motorcycle",
      +      "description": "A motorcycle, moped or tricycle.",
      +      "type": "string"
      +    },
      +    {
      +      "const": "motorhome",
      +      "description": "A motor caravan or campervan.",
      +      "type": "string"
      +    }
      +  ]
      +}
    • addedInput schema / $defs / OptimiseVehicleSpec / properties / reloads
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/ReloadsSpec"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Let this vehicle return to a depot, reload and go out again — the\nwaste-collection tipping round, the van that comes back for a\nsecond wave of parcels."
      +}
    • addedInput schema / $defs / OptimiseVehicleSpec / properties / territory_ids
      Added value: +{
      +  "description": "Ids of the request's `territories` this vehicle may work in.\nOmitted or empty, the vehicle is UNRESTRICTED and may serve any\ntask, inside a territory or outside every one of them. Listed, the\nvehicle may serve a task only if that task sits inside at least one\nof the named territories.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
    • addedInput schema / $defs / RelaxSpec
      Added value: +{
      +  "description": "What the caller is willing to give up if the first solve leaves work\nunassigned. At least one field is required.",
      +  "properties": {
      +    "allow_overtime_s": {
      +      "description": "Extend every vehicle's shift END by this many seconds. Shift starts\nare never moved earlier — a driver cannot begin before they begin.",
      +      "format": "int64",
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    },
      +    "time_windows_by_s": {
      +      "description": "Widen every task time window by this many seconds at EACH end. A\n09:00–12:00 window with 1800 becomes 08:30–12:30.",
      +      "format": "int64",
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / $defs / ReloadsSpec
      Added value: +{
      +  "description": "A vehicle's multi-trip reload plan.",
      +  "properties": {
      +    "depot": {
      +      "anyOf": [
      +        {
      +          "$ref": "#/$defs/LatLon"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Where the vehicle reloads. Omitted, its own `start` is used (or its\n`end` if it declared only that)."
      +    },
      +    "max_trips": {
      +      "description": "How many trips this vehicle may run in its shift, 2–5. A BUDGET,\nnot a prediction: the shift is cut into that many fixed windows\nbefore the solve, so asking for five trips on a shift that supports\nthree shrinks every window to a fifth and can make the whole day\nworse. Ask for the number of trips you actually expect to run.",
      +      "format": "uint32",
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    "reload_time_s": {
      +      "description": "Seconds at the depot between trips — tipping, reloading, the\nweighbridge. Held out of the shift before it is partitioned, so it\nis never accidentally spent driving.",
      +      "format": "uint32",
      +      "minimum": 0,
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    }
      +  },
      +  "required": [
      +    "max_trips"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / $defs / TerritorySpec
      Added value: +{
      +  "description": "One named territory: a polygon that bounds which vehicle may serve\nwhich stop.",
      +  "properties": {
      +    "id": {
      +      "description": "Caller-chosen id, echoed back and referenced by\n`vehicles[].territory_ids`. Must be unique within the request.",
      +      "type": "string"
      +    },
      +    "polygon": {
      +      "description": "The outer ring as GeoJSON `[lon, lat]` positions — longitude\nFIRST. Closed or open; an unclosed ring is closed for you.",
      +      "items": {
      +        "items": {
      +          "format": "double",
      +          "type": "number"
      +        },
      +        "maxItems": 2,
      +        "minItems": 2,
      +        "type": "array"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "id",
      +    "polygon"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / properties / avoid_zones
      Added value: +{
      +  "description": "Keep the optimisation's travel-time matrix out of every zone the\ndeclared vehicle would be charged or banned in. Requires\n`emissions`.",
      +  "type": [
      +    "boolean",
      +    "null"
      +  ]
      +}
    • addedInput schema / properties / emissions
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/EmissionsSpec"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The fleet's emission declaration, for UK clean-air / low-emission\nzone assessment. On its own it annotates: the response's `zones`\nblock names every zone containing one of the problem's own\nlocations and what this vehicle would pay there. With\n`avoid_zones` it also steers the internal travel-time matrix away\nfrom those zones, so the plan itself changes."
      +}
    • addedInput schema / properties / relax_if_unassigned
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/RelaxSpec"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Re-solve ONCE with these relaxations if the first solve leaves work\nunassigned, and say honestly which plan came back. At most one\nsecond solve, never beyond the caps you state, and the relaxed plan\nis returned only if it assigns MORE work than the first — giving\naway constraints for nothing is strictly worse than not giving them\naway. Breaks are never widened, nor are capacities, skills,\nterritories or task caps: only time windows move, and only by the\nstated amounts. Bills as two solves when the second one runs."
      +}
    • addedInput schema / properties / territories
      Added value: +{
      +  "description": "Fleet territories: named polygons that bound which vehicle may\nserve which stop, referenced by `vehicles[].territory_ids`. These\nare request data — caller-drawn rounds, validated per call and\nnever stored. Nothing to do with clean-air zones or with the\noffline map packages of the same word.",
      +  "items": {
      +    "$ref": "#/$defs/TerritorySpec"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / relaxation
      Added value: +{
      +  "description": "The relaxation report: the caps requested, whether a second solve\nran, whether ITS plan is the one returned, what was widened, and\nwhat is still unassigned. Present only when `relax_if_unassigned`\nwas declared.\n\nAlways read `second_solve` and `relaxed_plan_used` before telling\nanyone the day fits. A plan produced under relaxation has had\npromises moved, and the block is what says so."
      +}
    • addedOutput schema / properties / reloads
      Added value: +{
      +  "description": "The multi-trip split: each vehicle's trips, their windows, the\ndepot each returns to, and the stated approximation. Present only\nwhen a vehicle declared `reloads`.\n\nRead the `basis` inside it before quoting arrival times. The trip\nwindows are fixed BEFORE the solve, so a lorry that tips early\ncannot lend the spare time to its next trip: stops can come back\nunassigned that a truly sequential model would have served. The\nplan is feasible, never optimistic — it cannot put a vehicle in two\nplaces at once — but it is not optimal. Re-plan after each tip\nthrough `replan_routes` for the tighter answer."
      +}
    • addedOutput schema / properties / territories
      Added value: +{
      +  "description": "How the territories bound the plan: which vehicle was eligible for\nwhat, and any task no eligible vehicle existed for. Present only\nwhen `territories` was declared."
      +}
    • addedOutput schema / properties / zones
      Added value: +{
      +  "description": "Clean-air / low-emission zones touching the problem's own\nlocations, and what the declared vehicle pays in each. Present only\nwhen `emissions` was declared."
      +}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

No annotations were provided, so the description carries the full burden. It discloses the most important behavioral trait: `relax_if_unassigned` re-solves exactly once, returns the relaxed plan only if it assigns more work, and bills as two solves. It also warns that reloads is an approximation, that max_trips is a budget not a prediction, and that the user must check `relaxation.relaxed_plan_used` before claiming the day fits. This is rich, honest behavioral context.

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 long, but every sentence earns its place — it explains the VRP inputs, costing profile rules, fair-use limits, territory semantics, reload behavior, relaxation guarantees, emissions effects, and the gateway prerequisite. It is front-loaded with the core purpose and returns. It loses one point for being quite dense and long; an agent may need to re-read parts, but the density is justified by the tool's complexity.

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 the tool's high complexity (9 parameters, nested specs, output schema), the description covers all the critical decision points: when to use alternatives, what happens with reloads, what relaxation actually changes, the MapMap gateway dependency, the 200-location/400 km limit, and the honest-check caveats. The output schema exists, so the description need not enumerate return fields; it adds the operational context the schema cannot.

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?

The schema description coverage is 100%, so the baseline is 3; however, the description adds semantic value beyond the schema by explaining how `vehicles`, `jobs`, and `shipments` interact, what `territories` polygon order requires (longitude first), how `reloads` splits the shift, what `relax_if_unassigned` actually does, and how `emissions` with `avoid_zones` changes the plan. This goes well beyond what the JSON Schema 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 opens with a clear, specific statement — 'Optimise multi-vehicle, multi-stop delivery plans (VRP)' — and then details the core inputs (vehicles, jobs, shipments), costing modes, and return shape. It also explicitly differentiates itself from nearby siblings like `cluster`, `submit_optimise_job`, and `replan_routes`.

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 `cluster` then optimise each group when exceeding 200 unique locations or 400 km span, use `submit_optimise_job` for 2,000 locations, and use `replan_routes` after each tip. It also states the tool refuses to run without a MapMap gateway for territories/reloads/relaxation/zones, which is important when-to-use/not-use information.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Most tools target a distinct action and resource pair, and descriptions are explicit about which tool fits which scenario. The closest overlaps—plan_ev_route vs cheapest_charging_along_route, and route vs plan_day vs order_stops vs optimise_routes—are mitigated by clear guidance, so an agent can usually pick correctly.

Naming Consistency4/5

Tool names overwhelmingly follow a verb_noun snake_case pattern (plan_ev_route, set_palette, list_style_layers) with a consistent geo_ prefix for geometry helpers. Minor deviations like elevation, route, and matrix are short and readable but break the strict verb_noun convention.

Tool Count2/5

At 39 tools, this surface is well past the 25+ threshold and feels heavy even for a broad mapping platform. The set spans routing, geocoding, places, styles, EV/fuel, telematics, usage, and feedback, which would be easier for an agent to navigate if split into smaller domain-focused servers.

Completeness4/5

For the stated breadth, coverage is strong: routing, multi-stop planning, VRP, EV/fuel detours, geocoding, places, geometry, style lifecycle, and telematics all have workable primary paths. Minor gaps like no style deletion, no route alternatives, and no batch geocoding are present but do not create dead ends for core workflows.

Resources