Skip to main content
Glama
Sign In
PVsyst CLI MCP

PVsyst CLI MCP

by Anonymousnake
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

pvsyst_run_sourced_house_task

Prepare a PVsyst source project from cited inputs and run the annual simulation for one house design.

Instructions

[Simulation] Bind cited inputs, prepare a source project without an annual run, then deliver one house. design reuses SingleDesignRequest, but module/inverter require exact loose file_name and capacity/electrical_design must be absent: the existing cited-source helper builds the electrical draft. sources/declarations/goals reuse pvsyst_prepare_sourced_design semantics; an explicit design.target_dc_kw is also an engineering goal, never a guessed rating. Missing/mismatched citations return needs_context and the concrete draft without writes. design.new_project is the NEW source; spec.new_project is a DISTINCT final house project. Complete house/layout/module geometry reuse the existing native house input contract. Dry-run on a fresh source is ready_for_preparation or ready_for_weather, not full house preflight; it writes nothing and launches no GUI. Execution requires dry_run=false AND confirm=true. Source review additionally requires accept_source_review=true, and remains needs_review in the final result; confirmation never certifies source authenticity. Prepared source and house manifests own recovery: resume rechecks request/provenance, canonical inputs and prepared files, then resumes the existing child checkpoint without another preparation/annual baseline. Partial source preparation remains inspectable via its existing recovery transactions, not automatically repeated or silently overwritten. Final annual execution is only the existing native house task. GUI/version/DPI/topology bounds are unchanged. Existing user windows are not taken over, INI is not edited here. Weather assets/source review are checked; the house path does not add hourly comparison against the source weather CSV. It reports weather_native_comparison_performed=false. Raw source text is not persisted or echoed; accepted citation provenance is preserved. No new PV/sizing/dispatch model or general job framework.

Input Schema

NameRequiredDescriptionDefault
specYes
resumeNo
confirmNo
dry_runNo
retry_simulationNo
accept_source_reviewNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so unusually well: it covers dry-run writes, confirm/accept_source_review requirements, needs_context returns, resume/recovery behavior, no GUI takeover, no INI edits, and raw source text not being persisted or echoed. These are substantive side-effect and safety disclosures beyond what the schema states.

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 purpose is front-loaded, and most sentences contain relevant behavioral or constraint information. However, the body is a dense, clause-heavy paragraph with little structure, making it harder to parse than necessary for an agent.

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 orchestration tool with no annotations and no output schema, the description supplies many important statuses, gates, and non-actions. It still omits explicit sibling routing and leaves one top-level parameter (retry_simulation) undocumented, so it is adequate but not complete.

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?

The description adds important cross-field meaning: module/inverter require exact loose file_name, capacity/electrical_design must be absent, design.new_project differs from spec.new_project, and target_dc_kw is an engineering goal. But with 0% schema description coverage, it still leaves retry_simulation completely unexplained and gives only by-reference semantics for sources/declarations/goals.

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 opening sentence states specific actions: bind cited inputs, prepare a source project without an annual run, then deliver one house. Later text clarifies that final annual execution is the existing native house task, distinguishing this from pure preparation. However, 'deliver one house' and the overloading of new_project remain somewhat jargon-heavy.

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

Usage Guidelines2/5

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

The description gives prerequisites and execution gates, but never explicitly says when to choose this tool over pvsyst_run_house_task or pvsyst_prepare_sourced_design. It implies sourced/cited input usage but provides no clear alternatives, exclusions, or routing guidance.

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