Skip to main content
Glama
Knight60

ArcGIS Pro MCP

by Knight60
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

get_features

Read attribute rows from ArcGIS Pro layers, tables, or datasets using SQL filters, field selection, ordering, paging, and optional WKT geometry.

Instructions

Read attribute rows from a layer, table or dataset path, with an optional where clause, field subset, ordering and WKT geometry.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum rows to return (max 5000).
whereNoSQL where clause.
fieldsNoFields to return; default all.
offsetNoRows to skip -- use for paging.
map_nameNoMap to act on; defaults to the active map.
order_byNoORDER BY clause, e.g. "POP DESC".
layer_nameYesLayer or table name as shown by get_layers, or a full dataset path.
include_geometryNoAdd SHAPE@WKT geometry (can be very large).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv1.1.1
    • addedInput schema / properties / fields / description
      Added value: +"Fields to return; default all."
    • addedInput schema / properties / include_geometry / description
      Added value: +"Add SHAPE@WKT geometry (can be very large)."
    • addedInput schema / properties / layer_name / description
      Added value: +"Layer or table name as shown by get_layers, or a full dataset path."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum rows to return (max 5000)."
    • addedInput schema / properties / map_name / description
      Added value: +"Map to act on; defaults to the active map."
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Rows to skip -- use for paging.",
+  "title": "Offset",
+  "type": "integer"
+}
    • addedInput schema / properties / order_by
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "ORDER BY clause, e.g. \"POP DESC\".",
+  "title": "Order By"
+}
    • addedInput schema / properties / where / description
      Added value: +"SQL where clause."
  2. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does establish this as a read-only row-retrieval operation with no mutation implied, which is the key safety signal. It omits paging behavior, the default/max row caps, and whether the target layer must already exist, leaving moderate gaps.

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?

A single front-loaded sentence naming the action and its optional modifiers, with no filler. It is dense but every clause maps to real functionality, though the trailing clause list slightly crowds the core statement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool the description is thin, but the 100% schema coverage and existing output schema offload parameter and return-value documentation. What remains missing is behavioral context: pagination semantics, row-cap defaults, and default map targeting, which the description does not address.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter (where, fields, order_by, limit, offset, include_geometry, map_name) is already documented in the schema. The description only mirrors those capabilities at a high level without adding syntax, format, or defaulting detail, which is the expected baseline when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ("Read attribute rows from a layer, table or dataset path") and enumerates the supported query capabilities. An agent can distinguish it from count_features, summarize_features, and get_field_statistics. It does not, however, explicitly name which sibling to prefer for alternate query styles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, and no alternatives are named among the many read-oriented siblings (count_features, select_features, export_features). The optional clauses imply a filtered-read scenario but leave the agent to infer it.

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

Deploy Server

Other Tools