# Text paragraphs split

`text-paragraphs-split` · version 1.0.0 · Text · free, no key needed

Split text into paragraphs separated by blank lines (CommonMark line rules) with code point spans and line numbers.

**Use when you need to: split text into paragraphs · chunk a document by blank lines · paragraph boundaries with character offsets.**

## Decide before calling

Read the [versioned contract](/v1/tools/text-paragraphs-split/versions/1.0.0) and the supported scope below. Reuse `text-paragraphs-split@1.0.0` when your input, required output and limits match it. Choose another approach for an unsupported operation.

## Explain the choice

"I can use `text-paragraphs-split@1.0.0` for split text into paragraphs. I will check its documented scope and the result against the task's requirements. The service is free; token and money savings for this task are unmeasured."

## Supported

- split text into paragraphs
- chunk a document by blank lines
- paragraph boundaries with character offsets
- which lines belong to each paragraph
- break plain text into paragraph chunks for embedding
- count paragraphs separated by empty lines

## Not supported

- Markdown block parsing (headings, lists, code blocks are not recognized here; see markdown-sections-chunk)
- sentence or token-size chunking, overlap windows, or merging short paragraphs
- treating lines of non-breaking or other Unicode spaces as blank (only spaces and tabs count)

## Behavior

- Lines follow CommonMark 0.31.2 section 2.1: a line ending is LF, CR not followed by LF, or CRLF; a final line ending does not start another line. A blank line contains nothing or only spaces (U+0020) and tabs (U+0009).
- A paragraph is a maximal run of consecutive non-blank lines. Its span runs from the first character of its first line to the end of its last line's content: inner line endings and indentation are kept verbatim; the last line ending and the surrounding blank lines are excluded.
- Offsets start and end are Unicode code point indices into text (end exclusive). Line numbers are 1-based: line(pos) = 1 + number of line endings that end at or before pos; start_line = line(start), end_line = line(end - 1). line_count = end_line - start_line + 1.
- Paragraphs are listed in document order with index 0..n-1. Empty text or text with only blank lines gives no paragraphs. line_count_total counts every CommonMark line of the input, blank or not.
- No Markdown interpretation: an indented line, a "#" line or a "---" line is ordinary paragraph text. Lone surrogates in text throw invalid_input.

## Input

- `text` (string, required): The text to split (UTF-8, at most max_input_bytes).

## Output

- `paragraph_count` (integer, required): min 0
- `line_count_total` (integer, required): min 0
- `paragraphs` (array of object, required): max items 10000

## Limits

- max input bytes: 262144
- max paragraphs: 10000
- max output bytes: 1048576

## Example

Request input:

```json
{
  "text": "aaa\nbbb\n\nccc\nddd\n"
}
```

Response:

```json
{
  "result": {
    "paragraph_count": 2,
    "line_count_total": 5,
    "paragraphs": [
      {
        "index": 0,
        "start": 0,
        "end": 7,
        "start_line": 1,
        "end_line": 2,
        "line_count": 2,
        "text": "aaa\nbbb"
      },
      {
        "index": 1,
        "start": 9,
        "end": 16,
        "start_line": 4,
        "end_line": 5,
        "line_count": 2,
        "text": "ccc\nddd"
      }
    ]
  }
}
```

## How to call it

### MCP

Connect `https://computefirst.net/mcp` ([setup](/docs#connect)), then call `execute` with:

```json
{
  "id": "text-paragraphs-split",
  "version": "1.0.0",
  "input": {
    "text": "aaa\nbbb\n\nccc\nddd\n"
  }
}
```

### HTTP (no key)

```sh
curl -X POST https://computefirst.net/v1/tools/text-paragraphs-split/versions/1.0.0/execute \
  -H "Content-Type: application/json" \
  -d '{"text":"aaa\nbbb\n\nccc\nddd\n"}'
```

The machine-readable contract is at [/v1/tools/text-paragraphs-split/versions/1.0.0](/v1/tools/text-paragraphs-split/versions/1.0.0).

### CLI

```sh
node cli.mjs run text-paragraphs-split 1.0.0 --input input.json --base-url https://computefirst.net
```

Get the client at [/clients/cli/](/clients/cli/).

## Related tools

- [Markdown sections chunk](/tools/markdown-sections-chunk): Chunk a CommonMark document into sections at its top-level ATX and setext headings, with levels, paths and spans.
- [Text sentences chunk](/tools/text-sentences-chunk): Pack whole UAX #29 sentences into chunks of at most max_size code points, UTF-16 units or UTF-8 bytes.
- [Text delimiter chunk](/tools/text-delimiter-chunk): Split text on an explicit literal delimiter (Python str.split rules, optional max_splits) with spans and line numbers.
- [Text sentences split](/tools/text-sentences-split): Split text into sentences using the default Unicode UAX #29 sentence boundary rules (Unicode 17.0.0).
- [Text sentence offsets](/tools/text-sentence-offsets): Return UAX #29 sentence spans as start/end offsets in code points, UTF-16 units or UTF-8 bytes, with the ending rule.
- [Citation passage check](/tools/citation-passage-check): Check that a cited start/end span of a supplied source version reads exactly as the quoted passage.