EasyTerritory MCP

Split Territory

territory_split

Destructive

Territory split: divides one territory (e.g. an oversized one) into two while changing the rest of the alignment as little as possible (N to N+1 territories). Needs source_tal_id and target_territory_id, plus the Territory Solution from map_session_id (the open map) or ts_handle. Workload balance needs dwell_time; a missing id or dwell returns CLARIFICATION_REQUIRED with the question. Writes a new derived alignment; the source stays. Returns a task; the result carries disruption_summary (retention_pct).

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": "territory_split"
  }
}

Input Schema

Name	Required	Description	Default
`objective`	No
`ts_handle`	No	Territory Solution reference (tsh_...) from a build, ingest_accounts, import_geojson, import_designer_project, or get_map_visualization; Territory Solutions are not accepted inline.
`dwell_time`	No
`part_layer`	No	Part layer (e.g. us_zips). Required only when not inferable from the source TAL.
`point_layer`	No	Optional point layer used to compute per-part workload/metric measures. When omitted, a uniform geography-only weighting is used.
`new_tal_label`	No	Label for the derived TAL. Defaults to '<source label> (<operation>)'.
`repair_policy`	No	Topology repair for dissolved territories. default fills interior holes in the dissolved geometry (no part is added or reassigned; repair_summary.changed_part_ids lists the territories' own parts). report_only detects holes and changes nothing (warning REPAIR_AVAILABLE). strict fails with REPAIR_REQUIRED when a hole is found.	default
`source_tal_id`	No	Source TAL. Optional for form-capable clients that can answer via elicitation.
`map_session_id`	No	Open map session (msess_...) from get_map_visualization. Its Territory Solution is the input; omit ts_handle when set.
`balance_tolerance`	No	Accepted for compatibility. The power-diagram rebalance converges on its own internal tolerance, so this value no longer gates per-part moves.
`disruption_weight`	No	Incumbency stickiness for the warm-started power-diagram rebalance. 0 is a pure power re-solve (max balance, more churn); higher values keep more of the source alignment by requiring a neighbor territory to inflate further before it can claim a border part.
`new_territory_label`	No	Label for the second territory created by the split. Defaults to '<target> (split)'.
`target_territory_id`	No	Leaf territory (id or label) to split into two. Optional when elicitation can fill it.
`visit_frequency_field`	No	Numeric visits-per-cycle column on the point layer. When omitted, inherits from source TAL build_provenance or point-layer metadata.

Output Schema

Name	Required	Description
`ok`	Yes
`error`	No	Present when ok is false.
`result`	No	Present when ok is true. A submission returns the task reference (task_id, next_action, sleep_ms); the completed task result carries the remaining fields.
`warnings`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed16 schema fields changedNov 1, 2026

addedInput schema / properties / balance_tolerance / description

Added value: +"Accepted for compatibility. The power-diagram rebalance converges on its own internal tolerance, so this value no longer gates per-part moves."

addedInput schema / properties / disruption_weight / description

Added value: +"Incumbency stickiness for the warm-started power-diagram rebalance. 0 is a pure power re-solve (max balance, more churn); higher values keep more of the source alignment by requiring a neighbor territory to inflate further before it can claim a border part."

addedInput schema / properties / map_session_id / description

Added value: +"Open map session (msess_...) from get_map_visualization. Its Territory Solution is the input; omit ts_handle when set."

addedInput schema / properties / new_tal_label / description

Added value: +"Label for the derived TAL. Defaults to '<source label> (<operation>)'."

addedInput schema / properties / new_territory_label / description

Added value: +"Label for the second territory created by the split. Defaults to '<target> (split)'."

addedInput schema / properties / part_layer / description

Added value: +"Part layer (e.g. us_zips). Required only when not inferable from the source TAL."

addedInput schema / properties / point_layer / description

Added value: +"Optional point layer used to compute per-part workload/metric measures. When omitted, a uniform geography-only weighting is used."

addedInput schema / properties / source_tal_id / description

Added value: +"Source TAL. Optional for form-capable clients that can answer via elicitation."

addedInput schema / properties / target_territory_id / description

Added value: +"Leaf territory (id or label) to split into two. Optional when elicitation can fill it."

removedInput schema / properties / ts

Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Ts"
-}

addedInput schema / properties / ts_handle / description

Added value: +"Territory Solution reference (tsh_...) from a build, ingest_accounts, import_geojson, import_designer_project, or get_map_visualization; Territory Solutions are not accepted inline."

addedInput schema / properties / visit_frequency_field / description

Added value: +"Numeric visits-per-cycle column on the point layer. When omitted, inherits from source TAL build_provenance or point-layer metadata."

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / properties

Added value: +{
+  "error": {
+    "description": "Present when ok is false.",
+    "properties": {
+      "ask_user": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "code": {
+        "type": "string"
+      },
+      "details": {
+        "type": "object"
+      },
+      "do_this_next": {
+        "type": "object"
+      },
+      "message": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "ok": {
+    "type": "boolean"
+  },
+  "result": {
+    "description": "Present when ok is true. A submission returns the task reference (task_id, next_action, sleep_ms); the completed task result carries the remaining fields.",
+    "properties": {
+      "balance_summary": {
+        "type": "object"
+      },
+      "disruption_summary": {
+        "type": "object"
+      },
+      "do_this_next": {
+        "type": "object"
+      },
+      "expires_at": {
+        "type": "string"
+      },
+      "job_id": {
+        "type": "string"
+      },
+      "next_action": {
+        "type": "string"
+      },
+      "operation": {
+        "type": "string"
+      },
+      "repair_summary": {
+        "type": "object"
+      },
+      "sleep_ms": {
+        "type": "integer"
+      },
+      "solver_diagnostics": {
+        "type": "object"
+      },
+      "source_tal_id": {
+        "type": "string"
+      },
+      "status": {
+        "type": "string"
+      },
+      "tal_id": {
+        "type": "string"
+      },
+      "task_id": {
+        "type": "string"
+      },
+      "terminal": {
+        "type": "boolean"
+      },
+      "territory_count": {
+        "type": "integer"
+      },
+      "ts_handle": {
+        "type": "string"
+      },
+      "ts_identity": {
+        "type": "object"
+      },
+      "ts_omitted": {
+        "type": "object"
+      }
+    },
+    "type": "object"
+  },
+  "warnings": {
+    "items": {
+      "properties": {
+        "code": {
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "type": "array"
+  }
+}

addedOutput schema / required
```
Added value: +[
+  "ok"
+]
```

removedOutput schema / title

Removed value: -"territory_splitDictOutput"

Changed1 schema field changedOct 20, 2026

changedInput schema / properties / objective / anyOf

Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "description": "Balance objective: {metric: '<column>|__account_count__', workload_bias: 0..100, metric_bias: 0..100}. Biases sum to 100. For pure metric balance, pass {metric: '<column>', workload_bias: 0, metric_bias: 100} (or {metric: '<column>'} on restructure tools). When omitted on restructure tools, inherits the source TAL build_provenance objective or seed_build target.",
+    "properties": {
+      "metric": {
+        "description": "Point metric column name to balance (e.g. 'Revenue', 'weekly_volume'), or '__account_count__' for location-count balance.",
+        "type": "string"
+      },
+      "metric_bias": {
+        "description": "Weight (0..100) on the metric or location-count dimension.",
+        "maximum": 100,
+        "minimum": 0,
+        "type": "integer"
+      },
+      "workload_bias": {
+        "description": "Weight (0..100) on workload (drive time + dwell).",
+        "maximum": 100,
+        "minimum": 0,
+        "type": "integer"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed1 schema field changedOct 14, 2026

changedInput schema / properties / dwell_time / anyOf

Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "description": "Onsite (dwell) time per visit: {type: 'scalar', value: <number>, unit: 'minutes'|'hours'} or {type: 'field', field: '<column>', unit: 'minutes'|'hours'}.",
+    "properties": {
+      "field": {
+        "description": "Point column name holding per-account onsite time when type='field'.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "type": {
+        "description": "Dwell source: 'scalar' for a fixed per-visit duration or 'field' for an ingested point column.",
+        "enum": [
+          "scalar",
+          "field"
+        ],
+        "type": "string"
+      },
+      "unit": {
+        "default": "minutes",
+        "description": "Time unit for value or field ('minutes' or 'hours').",
+        "enum": [
+          "minutes",
+          "hours"
+        ],
+        "type": "string"
+      },
+      "value": {
+        "description": "Confirmed onsite duration per visit when type='scalar'.",
+        "minimum": 0,
+        "type": "number"
+      }
+    },
+    "required": [
+      "type"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed1 schema field changedOct 9, 2026

removedInput schema / properties / guidance_handle

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Guidance Handle"
-}

Changed2 schema fields changedOct 5, 2026

addedInput schema / properties / repair_policy / description

Added value: +"Topology repair for dissolved territories. default fills interior holes in the dissolved geometry (no part is added or reassigned; repair_summary.changed_part_ids lists the territories' own parts). report_only detects holes and changes nothing (warning REPAIR_AVAILABLE). strict fails with REPAIR_REQUIRED when a hole is found."

addedInput schema / properties / repair_policy / enum

Added value: +[
+  "default",
+  "strict",
+  "report_only"
+]

First observedSep 29, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond destructiveHint=true: it discloses that a new derived alignment is written while 'the source stays', that the call is asynchronous ('Returns a task'), what the result contains (disruption_summary/retention_pct), and how missing inputs surface (CLARIFICATION_REQUIRED). The minimal-churn guarantee ('changing the rest of the alignment as little as possible') is exactly the behavioral context annotations cannot express.

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?

Five dense sentences, all front-loaded with the operation and its outcome before inputs, error paths, and returns. No filler or restatement of the tool name.

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?

Covers the critical decision points for a 14-parameter, all-optional schema: which references are required, how imbalance is specified, how clarifications work, and what comes back. Optional tuning knobs (disruption_weight, objective biases, repair_policy) are left to the well-documented schema, which is a reasonable division of labor but leaves the description one step short of fully self-sufficient.

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?

With 86% schema coverage the baseline is 3, but the description adds real semantics: it pairs source_tal_id with target_territory_id as the required inputs despite both being schema-optional, makes map_session_id and ts_handle mutually exclusive, and flags dwell_time as the gate for workload balance. It does not explain disruption_weight, repair_policy, or the objective biases, which remain schema-only.

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?

Names a specific verb and resource ('divides one territory … into two') plus the cardinality outcome ('N to N+1 territories'), which immediately distinguishes it from territory_merge and territory_rebalance. The parenthetical use case ('e.g. an oversized one') tells the agent the problem this solves.

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?

States the two alternative input paths explicitly ('the Territory Solution from map_session_id (the open map) or ts_handle') and the failure condition ('a missing id or dwell returns CLARIFICATION_REQUIRED with the question'). It stops short of naming territory_merge/territory_rebalance as the alternatives for the opposite/different operations, so the routing guidance is strong but not exhaustive.

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

All EasyTerritory MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?