Skip to main content
Glama

build_plan

Runs a complete Loxone Config edit plan atomically, creating and connecting logic objects in one call, validating results, and saving to a new file only if validation passes.

Instructions

Runs a whole build plan in one call - all or nothing. Each step is a dict with 'op' and its arguments, e.g. {"op":"baustein","typ":"And","titel":"Rain and open","seite":"Page 2","als":"and1"} or {"op":"verbinden","von":"ha_rain","nach":"$and1","nach_eingang":"I2","seite":"Page 2"}. Ops (German keys, see plan.py): baustein, kopie, status, eingang, befehl, rs232, platzhalter, verbinden, trennen, werte, negieren, anzeige, statistik, position, loeschen, peripherie_loeschen, seite, mitteilung, kategorie_umhaengen, kategorie_loeschen. 'als' names a new object, '$name' refers to it. Missing placeholders are created by 'verbinden'. Afterwards the result is validated; with save_as (new file name) it is saved if validation passes.

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": {
      "steps": "<steps>"
    },
    "name": "build_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYes
save_asNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and delivers meaningful behavior: atomic all-or-nothing execution, post-execution validation, and a conditional save gated on validation with a new file name. It also discloses a non-obvious side effect — missing placeholders are created by 'verbinden'. It stops short of describing failure semantics (what the agent sees on partial-step failure) or that changes touch the loaded project in memory until saved.

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 description is front-loaded with the core contract ('all or nothing') and the save behavior is correctly placed last. Both inline examples and the op enumeration earn their space because the schema provides no item structure. The op list is dense but the parenthetical '(German keys, see plan.py)' is a reasonable compression rather than bloat.

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?

For a complex batch-mutation tool with no annotations, no output schema, and zero schema description coverage, the definition gives an agent enough to construct a first plan and understand atomicity and save behavior. But argument-level detail per op is outsourced to plan.py, so an agent cannot verify most step shapes from the definition alone. Adequate, with a clear substantive gap.

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 coverage is 0% and the steps array is an unconstrained object, so the description must compensate — and it largely does. It explains that each step is a dict with an 'op' key plus arguments, gives two concrete example dicts, enumerates all 20 valid ops, and defines the 'als' naming convention and '$name' reference syntax. The gap is per-op argument semantics: it points to plan.py rather than stating which arguments each op requires.

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?

The description opens with a specific verb and resource: 'Runs a whole build plan in one call - all or nothing.' The phrase 'in one call' and 'all or nothing' signals batch/atomic semantics, which distinguishes it from the singular siblings like block_add or page_add. It never names an alternative explicitly, so the differentiation is implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage context is implied rather than prescribed: the agent can infer this is the multi-step batching tool, and the note about validation-plus-save gives a hint about when saving occurs. However, there is no explicit 'use this instead of X when Y', no prerequisite statement, and no guidance on when to prefer individual op tools over a batch plan.

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