Skip to main content
Glama
OSM Edit MCP Server

OSM Edit MCP Server

by skywinder

review_node_create_duplicates

Read-only

Review blocking duplicate candidates for a node-create proposal, record evidence-backed decisions, and return a revised preview without writing to OpenStreetMap.

Instructions

Review every blocking candidate and return a new node-create revision.

Decisions bind exact candidate type, ID and expected_version. Every decision requires a reason and independent evidence_source. distinct_object resolves that match; same_object requires editing the existing object; uncertain stays blocked. Unknown candidates, omitted blockers and changed versions are rejected. This only stores a preview: review the new complete digest. After an explicit user request to publish it, call apply_osm_edit immediately; that tool performs the single final host confirmation. No OSM write or user approval occurs here. Superseded proposals cannot be applied.

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>",
      "decisions": "<decisions>"
    },
    "name": "review_node_create_duplicates"
  }
}

Input Schema

NameRequiredDescriptionDefault
decisionsYes
proposal_idYes
proposal_digestYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the annotations: decisions are bound to exact type/ID/expected_version, each needs a reason and independent evidence_source, unknown candidates, omitted blockers and changed versions are rejected, superseded proposals cannot be applied, and the output is only a stored preview that requires a later apply step. This is a rich disclosure of validation rules and side-effect boundaries that the readOnlyHint alone would not convey.

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 action and scope, then the decision rules, then the follow-up hand-off. Dense but mostly earning its sentences; some fragments ('distinct_object resolves that match') are terse to the point of ambiguity and could be tightened for readability.

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?

For a nested-schema tool with an output schema, this covers the essential flow, validation failures and the two-step publish path. What's missing is a definition of what makes a candidate 'blocking' and how the digest ties to the returned revision, but the core invocation requirements are present.

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%, so the description must carry the burden, and it does for the nested decision fields: it names osm_type, osm_id, expected_version, reason and evidence_source, and explains the three decision enum values semantically (distinct_object resolves the match, same_object requires editing the existing object, uncertain stays blocked). proposal_id and proposal_digest are only obliquely referenced ('superseded proposals', 'new complete digest'), leaving their exact role under-explained.

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?

States a specific verb and resource: reviews blocking duplicate candidates and produces a new node-create revision. It also separates itself from the write path (apply_osm_edit) and from OSM writes. Slightly held back by jargon like 'blocking candidate' and 'revision' that require domain inference, since the tool name is the only thing saying 'duplicates'.

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?

Clear routing: after an explicit user request to publish, call apply_osm_edit immediately, which performs the single final host confirmation. This tells the agent what this tool is not for (no OSM write, no user approval) and where to go next. It doesn't explicitly state the precondition that triggers a review (e.g., a stalled preview with unresolved blockers), so a bit of inference remains.

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