daedal-map

Overview Schema Source Related Servers Discussions Admin

Identify One Identifier Column's Reference System

identify_reference_system

Read-onlyIdempotent

Identify or verify the reference system for one column of geographic identifiers, returning country, level, vintage, and compatible geometry bank. Pass only identifier strings from that field.

Instructions

Single-column code-system classifier: use after an identifier column has already been selected, or to inspect one bounded set of like geography codes. Pass only identifier strings from that one field so leading zeros are preserved. It determines or verifies the system, country, level, vintage, and compatible geometry bank; it does not choose among dataset columns, convert the full dataset, or return polygons. Use identify_dataset_geography instead when column selection is still unknown. Ambiguous results remain unselected until the caller retries with expected.system; a known system can be verified by supplying expected on the first call. No payment required.

Input Schema

TableJSON Schema

Name	Required	Description
`expected`	No
`identifier`	No	One geography identifier to inspect.
`request_id`	No	Optional caller-supplied request id for tracing.
`identifiers`	No	A bounded representative identifier sample. Duplicate values are checked once. Values must be strings so leading zeros are preserved.
`country_scope`	No	Optional ISO3 country hint used to narrow candidate banks.
`dataset_context`	No	Bounded, non-row dataset clues used to rank plausible interpretations without replacing exact identifier verification.
`validation_scope`	No	Describes whether the bounded input is a sample or, only when it fits the identification cap, the complete distinct-key set. This tool validates every supplied identifier; create_conversion_job validates every row in the full dataset.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	No
`error`	No
`limit`	No
`reason`	No
`status`	No
`batch_id`	No
`guidance`	No
`warnings`	No
`next_step`	No
`candidates`	No
`request_id`	No
`column_count`	No
`clarification`	No
`meter_receipt`	No
`review_required`	No
`identifier_count`	No
`coordinate_binding`	No
`settlement_receipt`	No
`recommended_binding`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.1Sep 24, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": true,
+  "anyOf": [
+    {
+      "required": [
+        "ok",
+        "status",
+        "candidates"
+      ]
+    },
+    {
+      "required": [
+        "error"
+      ]
+    }
+  ],
+  "properties": {
+    "batch_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "candidates": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "clarification": {
+      "type": "object"
+    },
+    "column_count": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "coordinate_binding": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "error": {
+      "additionalProperties": true,
+      "properties": {
+        "code": {
+          "type": "string"
+        },
+        "details": {
+          "type": "object"
+        },
+        "message": {
+          "type": "string"
+        },
+        "retry_hint": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "code",
+        "message"
+      ],
+      "type": "object"
+    },
+    "guidance": {
+      "type": "object"
+    },
+    "identifier_count": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "limit": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "meter_receipt": {
+      "type": "object"
+    },
+    "next_step": {
+      "additionalProperties": true,
+      "anyOf": [
+        {
+          "required": [
+            "action"
+          ]
+        },
+        {
+          "required": [
+            "tool"
+          ]
+        }
+      ],
+      "properties": {
+        "action": {
+          "type": "string"
+        },
+        "arguments": {
+          "type": "object"
+        },
+        "tool": {
+          "type": "string"
+        },
+        "url": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "recommended_binding": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "request_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "review_required": {
+      "type": "boolean"
+    },
+    "settlement_receipt": {
+      "type": "object"
+    },
+    "status": {
+      "type": "string"
+    },
+    "warnings": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

AddedSep 24, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds substantial context: 'No payment required', 'does not choose among dataset columns, convert the full dataset, or return polygons', and the retry behavior for ambiguous results. It also explains that input values must be strings to preserve leading zeros. These add real value beyond the annotations and clarify what the tool will and won't do.

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?

The description is dense but every sentence earns its place: purpose, usage condition, input guidance, scope exclusions, alternative routing, retry behavior, and payment. It is front-loaded with the core purpose and has no fluff or redundancy.

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 tool with 7 parameters, nested objects, anyOf constraints, and an output schema, the description covers selection logic, input constraints, behavioral exclusions, and alternative routing. The output schema handles return details, and the description leaves no critical gap for an agent deciding whether and how to call it.

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 86%, so the baseline is 3. The description adds meaningful guidance: passing only strings from one field to preserve leading zeros, using expected.system for verification or retry, and clarifying dataset_context as 'bounded, non-row dataset clues' and validation_scope as covering every supplied identifier. These clarifications go beyond the schema, though they don't enumerate every parameter.

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?

States it is a 'single-column code-system classifier' and lists exactly what it determines (system, country, level, vintage, compatible geometry bank). Explicitly distinguishes from identify_dataset_geography by naming the sibling and the condition that selects it. The verb and resource are specific and unambiguous.

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?

Provides explicit when-to-use ('use after an identifier column has already been selected, or to inspect one bounded set') and when-not ('Use identify_dataset_geography instead when column selection is still unknown'). Also instructs to pass only identifier strings to preserve leading zeros and explains how to use expected for verification or retry. Clear, actionable guidance with a named alternative.

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

Deploy Server