OSM Edit MCP Server

Overview Schema Source Related Servers Discussions Admin

preview_node_create

Read-only

Preview a new OpenStreetMap POI without writing to OSM: validate coordinates and tags, search for nearby duplicate candidates, and review geometry, diff, and digest before applying.

Instructions

Preview one new POI without writing to OSM.

Coordinates must be finite, in range and exact at OSM's seven decimal places. Supply 1..20 nonempty string tags including an explicit POI classification and the actual independent evidence source. Requires verified OAuth/write_api. Searches the configured OSM API within about 100m; classifies nearby geometry by explicit POI type, sport, distance and identity signals. Blocking candidates need review_node_create_duplicates. That tool creates a new digest; it never uploads or approves a write. Failed or incomplete searches never establish absence. Review the exact geometry, tags, diff and full SHA-256 digest before a later apply_osm_edit. After an explicit user request to publish it, call apply_osm_edit immediately; it performs the single final MCP-host elicitation.

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": {
      "latitude": "<latitude>",
      "longitude": "<longitude>",
      "tags": "<tags>",
      "changeset_comment": "<changeset_comment>",
      "changeset_source": "<changeset_source>"
    },
    "name": "preview_node_create"
  }
}

Input Schema

Name	Required	Description	Default
`tags`	Yes
`latitude`	Yes
`longitude`	Yes
`changeset_source`	Yes
`changeset_comment`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.3.0Oct 21, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is consistent with that ("never uploads or approves a write"). Beyond annotations it discloses the auth scope required, the ~100m search radius, the classification signals used for nearby geometry, the blocking-candidate handoff, and where the single MCP-host elicitation occurs — substantive behavior an agent could not infer from structured fields.

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?

Front-loaded with the core statement, and the workflow, auth and validation facts all earn their place. It is a single dense block of short fragments with no visual grouping, which makes the ordering constraints slightly harder to scan than necessary, but there is no filler.

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?

Given an output schema exists, return values need no explanation, and the description covers safety, prerequisites, alternatives, follow-up dispatch and failure semantics ("Failed or incomplete searches never establish absence"). The only real gap is the unaddressed changeset_comment/changeset_source parameters, which an agent must guess at for a required-field tool.

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 0% and all five parameters are required, so the description must carry the load. It does well for latitude/longitude (finite, in range, exact at seven decimals) and tags (1..20 nonempty strings including an explicit POI classification and independent evidence source), but changeset_comment and changeset_source are never mentioned anywhere, leaving two required parameters undocumented.

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?

Opens with a specific verb, resource and scope: "Preview one new POI without writing to OSM." It immediately separates itself from the write path (apply_osm_edit) and the duplicate-review path (review_node_create_duplicates), so an agent can place it in the workflow 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 Guidelines5/5

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

Gives explicit sequencing: preview here, hand blocking candidates to review_node_create_duplicates, then call apply_osm_edit immediately after an explicit user request to publish. It also states the prerequisite (verified OAuth/write_api) and the ordering constraint that the geometry, tags, diff and SHA-256 digest must be reviewed before applying.

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