Skip to main content
Glama
OSM Edit MCP Server

OSM Edit MCP Server

by skywinder

preview_poi_polygon_create

Read-only

Preview a closed four-corner POI polygon before upload, validating geometry and limits without changing OSM data, and optionally staging an isolated node replacement for review.

Instructions

Preview four ordered corners as a closed POI area, without uploading.

Supply exactly four distinct latitude/longitude pairs at OSM precision. The server creates four untagged vertices and one closed way bearing all POI tags. No self-intersections, collinear corners, polar/dateline geometry or diameter over 500m. Searches the WHOLE polygon plus a 100m margin. Optional replace_node_id and expected_node_version explicitly replace one isolated, unchanged POI node inside the area, preserving all its tags on the new way and deleting it atomically. Parent ways/relations block this. demonstration=true permits synthetic geometry only on the official dev API; changeset_source must say synthetic or demonstration. Never infer a real boundary from one point. Review geometry, any deletion and the full digest; after an explicit user request to publish it, call apply_osm_edit immediately; it performs the single final digest-bound host confirmation.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "corners": "<corners>",
      "tags": "<tags>",
      "changeset_comment": "<changeset_comment>",
      "changeset_source": "<changeset_source>"
    },
    "name": "preview_poi_polygon_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsYes
cornersYes
demonstrationNo
replace_node_idNo
changeset_sourceYes
changeset_commentYes
expected_node_versionNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A4.4/5.0
Behavior4/5

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

The description goes well beyond the annotations: it discloses the exact server output (four untagged vertices plus one closed way carrying the POI tags), the duplicate search scope (whole polygon plus 100m margin), the atomic replace/delete semantics with expected_node_version, and the digest-bound confirmation handoff. One ambiguity remains: 'deleting it atomically' sits uneasily beside readOnlyHint=true and destructiveHint=false, and it is not spelled out that the deletion happens only at apply time, which could mislead a skimming agent even though it is not a true contradiction.

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 definition is information-dense and front-loaded, leading with what the tool does and deferring constraints and the workflow handoff to later sentences; nearly every clause carries a constraint the agent needs. Some sentences stack several rules without separators ('No self-intersections, collinear corners, polar/dateline geometry or diameter over 500m'), which slightly hurts scannability.

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 seven-parameter tool with nested objects and an output schema, the description covers geometry validation, tag handling, node replacement preconditions, environment restrictions on demonstration mode, duplicate-search scope, and the follow-up call to apply_osm_edit. Return values and the digest contents are properly left to the output schema, and nothing material is missing for a correct invocation.

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 0% across seven parameters, so the description must carry the load, and it largely does: it constrains corners (exactly four, distinct, ordered, OSM precision, no self-intersection/collinearity/polar geometry), binds tags to the resulting way, ties replace_node_id to expected_node_version and an isolated unchanged node, and restricts demonstration/changeset_source to the dev API with 'synthetic' or 'demonstration' labels. changeset_comment is required but never explained, and latitude/longitude format and precision are only implied by 'OSM precision'.

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 gives a specific verb, resource, and scope: 'Preview four ordered corners as a closed POI area, without uploading.' The 'without uploading' clause immediately separates it from apply_osm_edit, which the description later names as the publishing step, so an agent can tell the two apart without opening a schema.

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?

It names the alternative explicitly ('after an explicit user request to publish it, call apply_osm_edit immediately') with the condition that selects it, and gives a hard exclusion ('Never infer a real boundary from one point'). It also states preconditions that block the operation (parent ways/relations, diameter over 500m, degenerate geometry), though it does not contrast itself against preview_node_create or the review_* siblings.

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