Skip to main content
Glama

Validate NeonPlan 3D plan

neonplan_validate_plan
Read-onlyIdempotent

Validate a NeonPlan 3D building for structure, broken references, and unknown Home Assistant areas or entities before saving, without writing any changes.

Instructions

Check a NeonPlan 3D building for structure, broken references and unknown HA areas or entities without saving it.

Checks what the integration's schema requires (keys, types, main ranges), then what it does not check: duplicate ids, an opening's room_id/edge and offset ± width/2 inside that wall, repeated first corner, degenerate rooms, entity fields that are not an entity id/null/ none, furniture and pins outside every room; with check_ha, each area_id against HA's area registry and each entity id against HA's states. Warnings cover null fields NeonPlan binds automatically from the area. Writes nothing.

Use when: before neonplan_save_plan, or auditing the stored plan. Not for: saving — neonplan_save_plan runs this itself. Returns: {"valid", "errors": [...], "warnings": [...], "summary"} plus plan/revision when the stored plan was checked. Errors: invalid_plan, plan_not_found, neonplan_not_installed, ha_unreachable. Limits: ranges the schema checks but this does not are caught by the server at save time (invalid_building).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "neonplan_validate_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
planNoPlan id from `neonplan_list_plans`; `main` (default) is the plan every install has.main
buildingNoBuilding object to check (as `neonplan_get_plan` returns it); omit to check the stored plan.
check_haNoTrue (default) also checks every area_id and entity id against the live Home Assistant.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.29.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data; the description nonetheless adds real detail: which validation classes run by default vs. only with check_ha, that null-field warnings are informational, that nothing is written, and the enumerated error codes. It stops short of explaining warning severity or whether errors are all reported or first-failure only, which keeps it below a 5.

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-loads the one-line purpose, then uses labeled blocks (Use when / Not for / Returns / Errors / Limits) that an agent can scan. The middle paragraph enumerating internal checks is dense and borderline over-detailed, but it earns its place by explaining what errors and warnings will mean.

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?

Even though an output schema exists, the description still states the return shape, the conditional plan/revision fields, the full error set, and the documented limit (schema-only range checks surface later as invalid_building). For a validator whose results must be interpreted, this is complete enough to call correctly and act on the result.

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 coverage is 100%, so all three parameters are already documented in the schema, including check_ha's live-HA behavior. The description adds only marginal meaning beyond that — it reinforces when check_ha's registry checks apply but introduces no new syntax, defaults, or edge cases. Baseline 3 is appropriate.

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?

States a specific verb and resource ("Check a NeonPlan 3D building") and names the scope precisely: structure, broken references, unknown HA areas/entities, and explicitly "without saving it." The closing "Not for: saving — neonplan_save_plan runs this itself" cleanly separates it from the nearest sibling.

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?

Explicit "Use when: before neonplan_save_plan, or auditing the stored plan" plus an explicit exclusion naming the alternative tool that subsumes this check. Both the positive trigger and the anti-pattern are stated, so no inference is required.

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