siglent-sds-mcp

get_waveform

Read-only

Downloads voltage and time arrays from a selected oscilloscope channel for signal analysis, with a configurable point limit to control detail and context usage.

Instructions

Download waveform data from a channel. Returns voltage and time arrays reconstructed from the raw oscilloscope data. By default returns up to 1000 points (downsampled from full memory depth).

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": {
      "channel": "<channel>"
    },
    "name": "get_waveform"
  }
}

Input Schema

Name	Required	Description	Default
`channel`	Yes	Channel to download waveform from (C1, C2, C3, or C4)
`max_points`	No	Maximum number of data points to return (default 1000). Higher values give more detail but use more context.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv2.0.0Nov 13, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / max_points / maximum
```
Added value: +1000000
```
- addedInput schema / properties / max_points / minimum
```
Added value: +1
```
- changedInput schema / properties / max_points / type
```
Previous value: -"number"New value: +"integer"
```
First observedv1.0.1May 6, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=true, so the description carries the rest: it discloses that data is reconstructed from raw oscilloscope memory, that a lossy downsample occurs by default, and that full memory depth lies behind the default. It does not state units, sample interval, or error behavior when the channel is off, which is why this is not 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.

Conciseness5/5

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

Three short sentences, front-loaded with the action, then the return shape, then the default data quantity. No filler or redundant restatement of the tool name.

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 two-parameter read-only tool with no output schema, the description adequately explains what comes back (voltage and time arrays) and how volume is controlled. Missing only return-data details an agent might want, such as units or ordering, before trusting the arrays blind.

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% and both parameters are documented in the schema, including the max_points default and context tradeoff, so baseline 3 applies. The description's only addition is that the default view is downsampled from full memory depth, which is useful but marginal.

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?

"Download waveform data from a channel" gives a specific verb and resource, and the follow-up sentence specifies the returned payload (voltage and time arrays reconstructed from raw oscilloscope data). That distinguishes it from a settings-oriented sibling like get_channel, though no sibling is named explicitly.

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?

There is no guidance on when to call this versus measure, measure_statistics, or screenshot, nor any prerequisites such as whether the channel must be enabled or acquisition running. The only practical hint is the default 1000-point downsampling, which concerns data volume rather than tool selection.

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

Deploy Server