Skip to main content
Glama
PVsyst CLI MCP

PVsyst CLI MCP

pvsyst_import_house_pv_scene

Imports a generated house/PV scene into an open PVsyst project, assigns regions to source orientations, verifies native geometry, and saves a new variant for simulation.

Instructions

[Projects & Variants] Import a generated house/PV scene using the already open native PVsyst GUI. This bounded Windows path targets Chinese PVsyst 8.1.6 rev49278 with native logical DPI96 and the recorded physical window metrics, with the matching workspace and recipe project already open on its project page. Supports one or two PV regions; creation/standard export retains its 64-region limit. Unknown GUI metrics, dialogs, source/PAN mismatches and unsupported scene dialects stop rather than patching private VC data or guessing control positions. dry_run reads state only: no activation, key/mouse input or clipboard access. Execute with dry_run=false AND confirm=true, then leave the native desktop alone: selects the clean source variant, imports PVC2 and assigns its regions to the declared source orientation(s). The bounded two-orientation path explicitly places each table and verifies native SHD/saved VC geometry and a real GUI reload. It then runs PVsyst's scene-validity check and shading table, and saves a NEW native variant with the explicit display title variant_name (1..80 printable UTF-8 bytes). Native warnings beyond the expected beta notice stop; invalid geometry is returned as the software's own text. Any failure leaves the current window for inspection; an already-created variant path is disclosed even if postchecks fail. No automatic retry, source overwrite, application start/exit or INI modification is performed. Native validity text replaces the clipboard only after this confirmed operation; only the newly copied native text is read, never the earlier clipboard. imported/native_geometry_verified become true only after native persistence checks; native_consumption_verified stays false until a separate native simulation. shading_mode=module_layout additionally uses native placement and automatic string allocation, then selects detailed electrical shading. This opt-in requires two fixed source groups, one landscape zero-spacing table and one independent string (1..100 modules, one inverter/MPPT) per source array1/2. The saved module cells and native table/array links are checked; the selected mode is checked after GUI reload. Use pvsyst_run_simulation on the returned variant for energy/shading consumption. method="native" (opt-in) builds a NEW native input variant from the same supported recipe without any GUI, INI, clipboard, licence or engine action. It supports only two fixed orientations, two landscape zero-spacing tables, source arrays 1/2 with one independent string/inverter/MPPT each and the same PAN/OND; unsupported recipes stop before writing. dry_run builds and verifies the native records in memory only. Execution requires dry_run=false AND confirm=true and writes one new variant; the status is native_variant_created; stored_geometry_verified/stored_module_layout_verified reflect the STORED record only, while native_geometry_verified/native_module_layout_verified, native_consumption_verified and imported stay false because PVsyst has not loaded or consumed it; run an explicit simulation to verify consumption. dry_run writes nothing and keeps both stored flags false but still reports the passed precheck. The source variant/PAN are never modified.

Input Schema

NameRequiredDescriptionDefault
methodNogui
confirmNo
dry_runNo
scene_nameYes
shading_modeNolinear
variant_nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly: dry_run reads state only, execute requires dry_run=false and confirm=true, no automatic retry/source overwrite/app start/exit/INI modification occurs, failures leave the window for inspection, and clipboard use is tightly scoped. It also discloses native-method behavior, verification flags, and the fact that native consumption remains unverified until a separate simulation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and largely front-loaded, but it is a single long paragraph with repeated dry_run/flag explanations across GUI and native modes. Much of the length is justified by tool complexity, but the structure could be clearer and less repetitive.

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 complex tool with no annotations and no output schema, the description covers prerequisites, failure modes, side effects, verification flags, and the next simulation step. It does not fully enumerate the return shape, but it provides enough context for an agent to call the tool correctly.

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 compensate for all six parameters. It explains method, dry_run, confirm, shading_mode, and variant_name constraints well, and gives enough context for scene_name indirectly, though some parameter-level format details remain implicit.

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 states a specific verb and resource: importing a generated house/PV scene, with both GUI and native method modes. It clearly distinguishes import behavior from variant creation, but it does not explicitly name a sibling such as pvsyst_create_house_pv_scene to route the agent between them.

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?

It gives strong usage context: an already open native PVsyst GUI, matching workspace and recipe project, bounded Windows/version assumptions, one- or two-region support, and opt-in method='native' limitations. It also directs post-import simulation to pvsyst_run_simulation, though it lacks a direct comparison with create_house_pv_scene.

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