Skip to main content
Glama
ossenna-hq

ltspice-mcp

by ossenna-hq

export_waveform

Export full-fidelity waveform samples to a CSV file for your own FFT, custom metrics, or cross-correlation, without decimation, preserving all data points.

Instructions

Full-fidelity waveform egress: write every sample of one or more signals to a CSV file on disk and return its path — for when you want to compute on the raw data yourself (FFT, custom metrics, cross-correlation) rather than read a scalar or a decimated envelope.

Lossless within the chosen window (no decimation — that is get_waveform's job). Works on transient (.tran), DC sweep (.dc), AC (.ac), and noise (.noise). Complex AC traces are written as magnitude(dB)+phase(deg) by default (complex_format selects re/im or both); phase is the wrapped np.angle — run np.unwrap yourself for a continuous curve. A stepped (.step / Monte-Carlo) run is written tidy/long: one row per (step, sample) with leading step_index/step_value columns, because each transient step has its own time vector. The observations list surfaces FACTS (rows written, window coverage, non-finite samples KEPT, the complex format used) — not verdicts.

Returns the CSV path plus row/column counts; read the file with your own tools. Sibling egress, don't confuse: get_waveform returns a DECIMATED envelope as numbers in your context (no file); plot_waveform renders an interactive PICTURE for a human. For a single scalar use signal_stats/query_value.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
t_endNoWindow end in SPICE notation.
formatNoResponse format: 'json' for structured data, 'text' for human-readable
job_idNoExport a specific run of a completed sweep/MC (or single) job instead of a raw_file path; pair with ``run_index``.
out_dirNoDirectory to write the CSV into (resolved under an allowed path; created if needed). Default: a '.ltspice-mcp/waveforms/' sidecar next to the circuit for a job_id, or next to the raw for a raw_file.
signalsNoTrace names to export (e.g. ['V(out)', 'I(R1)']) or 'all' for every non-axis trace. Device operating-point params work too, by name or shorthand (e.g. ['m1.gm', 'm1.gds', 'm1.id']) — across a `.dc` sweep with `.save @m1[…]` this is the gm/ID-table read, one CSV.all
t_startNoWindow start in SPICE notation (e.g. '1m', '100u', '1k'). Bounds the export by windowing, not decimation — full fidelity inside the window.
raw_fileNoPath to .raw result file. Pass this OR ``job_id`` (a job run), not both.
run_indexNo0-based run to read when ``job_id`` is given (default 0).
complex_formatNoHow complex AC traces become columns: 'mag_phase' = magnitude(dB) + phase(deg) [default], 're_im' = real + imag, 'both' = all four. Ignored for real-valued (.tran/.dc/.noise) traces.mag_phase

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNo
columnsNo
n_stepsNo
signalsNo
row_countNo
window_usedNo
column_countNo
observationsNo
analysis_typeNo
complex_formatNo
Behavior5/5

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

The description discloses extensive behavior beyond the sparse annotations (readOnly=false, etc.): lossless windowing, supported analysis types, complex AC formatting with wrapped phase, tidy/long stepped-run output, and the observations list surfacing facts not verdicts. It adds significant context that the annotations do not supply, fully shouldering the transparency burden.

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

Conciseness5/5

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

Though the description is long, every sentence earns its place: it covers purpose, supported analyses, complex handling, stepped-run format, observations, output contents, and sibling differentiation. It is front-loaded and efficiently structured, with no redundancy or filler.

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?

Given the tool's complexity (9 optional parameters, multiple analysis types, varied output formats) and the presence of an output schema, the description covers all essential aspects: it explains the CSV output path, row/column counts, observations, and edge cases (stepped runs, complex traces). It leaves no major gaps for an agent to resolve.

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 description coverage is 100%, so the schema already documents all 9 parameters in detail (e.g., t_start, complex_format, signals). The description adds some behavioral context (e.g., 'phase is the wrapped np.angle — run np.unwrap yourself') but it does not materially expand parameter semantics beyond what the schema provides. A 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?

The description opens with a specific verb+resource ('Full-fidelity waveform egress: write every sample of one or more signals to a CSV file on disk and return its path') and clearly distinguishes from siblings by contrasting with get_waveform (decimated envelope) and plot_waveform (interactive picture). It leaves no ambiguity about the tool's role.

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?

Explicitly states 'for when you want to compute on the raw data yourself' and names alternatives: 'sibling egress, don't confuse: get_waveform returns a DECIMATED envelope... plot_waveform renders an interactive PICTURE... For a single scalar use signal_stats/query_value.' This gives clear when/when-not guidance and points to relevant alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ossenna-hq/MCP_LTSpice'

If you have feedback or need assistance with the MCP directory API, please join our Discord server