OSM Edit MCP Server

Overview Schema Source Related Servers Discussions Admin

apply_track_road_edit

DestructiveIdempotent

Applies an approved OpenStreetMap track or road edit by submitting its exact proposal digest and requiring a final host confirmation before upload.

Instructions

Apply an exact dev-API digest with one final host confirmation.

After an explicit publish request, call this tool immediately without an extra chat question. confirm records the caller's intent; the tool still performs the single digest-bound MCP-host confirmation before upload.

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": {
      "proposal_id": "<proposal_id>",
      "proposal_digest": "<proposal_digest>",
      "confirm": "<confirm>"
    },
    "name": "apply_track_road_edit"
  }
}

Input Schema

Name	Required	Description	Default
`confirm`	Yes
`proposal_id`	Yes
`changeset_id`	No
`proposal_digest`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Sep 5, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Beyond the annotations (destructive=true, openWorld=true, idempotent=true), it discloses a non-obvious behavior: `confirm` only records caller intent and does not bypass the separate digest-bound MCP-host confirmation before upload. It still omits what happens on digest mismatch, what exactly is mutated upstream, and whether failures leave partial state.

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?

Short and mostly front-loaded: the mutation and its confirmation model come first, then the calling instruction. The 'dev-API digest' phrasing and the double emphasis on confirmation add slight redundancy but no real waste.

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?

Return values are covered by the output schema and the safety profile by annotations, which lowers the burden. However, for a destructive, open-world publish operation it should say what is being uploaded/created and how failures or stale digests are surfaced.

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%, so the schema supplies no per-parameter meaning. The description clarifies two of four parameters in passing (`confirm` records intent, the digest must match exactly), but leaves `proposal_id` and `changeset_id` completely unexplained.

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

Purpose3/5

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

The description has a clear verb ('Apply') but the object is described abstractly as 'an exact dev-API digest', with the actual effect only inferable from the phrase 'before upload'. It never states that it publishes a track/road edit proposal to OSM, so the agent must lean on the tool name to understand the resource.

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?

'After an explicit publish request, call this tool immediately without an extra chat question' gives a clear, actionable triggering condition and even resolves a procedural ambiguity (don't ask again). It stops short of naming the preview_track_road_edit sibling as the non-committing alternative or stating when not to call it.

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