StatsPAI

load_data

Read-only

Load datasets from files, URLs, CSV text, or JSON rows and get a reusable data_id handle with shape, dtypes, missing counts, and summary stats for later analysis.

Instructions

Load a dataset into the server and get a data_id handle. Source: data_path (file or URL), data_records (JSON rows) or data_csv (CSV text). Returns the handle plus shape, dtypes, missing counts, the first rows and a numeric summary. Pass data_id to any later tool instead of re-sending the file; chain transform_data to filter / reshape / winsorise / impute and get a new handle whose lineage is recorded in every result's data_provenance.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "load_data"
  }
}

Input Schema

Name	Required	Description	Default
`name`	No	Optional label recorded with the handle.
`detail`	No	Payload depth; agent is the fullest.	agent
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`dataset`	No	Built-in example by name (sp.list_datasets).
`data_csv`	No	Small inline table as CSV text.
`as_handle`	No	Cache the fit and return its result_id.
`data_path`	No	Absolute path of a data file on the server.
`result_id`	No	Handle of an earlier fit made with as_handle=true.
`data_columns`	No	Load only these columns.
`data_records`	No	Small inline table as row objects.
`data_sample_n`	No	Uniform random subsample of this many rows (seed 0).
`max_output_bytes`	No	Result byte budget (default 262144; 0 = none).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value by enumerating the returned payload (shape, dtypes, missing counts, first rows, numeric summary) and by disclosing that lineage is recorded in every result's data_provenance. It stops short of explaining handle lifetime, whether handles persist across sessions, or what happens on a duplicate load, which matters because the tool does create server-side state.

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?

Four sentences, front-loaded with the verb and the returned handle, then sources, then output, then the chaining contract. Every sentence carries information the agent cannot get from the structured fields.

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?

An output schema exists and annotations cover safety, yet the description still explains the return essentials and the handle-reuse model, which is the key calling convention. Slight gap: with 12 parameters it never mentions the built-in dataset shortcut, detail levels, or byte budget, relying wholly on the schema for those.

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 coverage is 100%, so the baseline would be 3, but the description adds meaning the schema does not: it frames data_path / data_records / data_csv as alternative mutually exclusive sources rather than additive ones, and clarifies that data_id replaces data_path. Parameters like detail, max_output_bytes, as_handle and data_sample_n are left entirely to the schema.

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?

Names a specific verb and resource ('Load a dataset into the server'), states the concrete payoff ('get a data_id handle'), and distinguishes the three source modes. An agent immediately knows this is the ingestion entry point and what it receives back.

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?

Gives explicit downstream guidance: 'Pass data_id to any later tool instead of re-sending the file' and 'chain transform_data to filter / reshape / winsorise / impute'. It does not say when not to use it (e.g. when data already has a handle, or how it relates to describe_data), which keeps it short of a 5.

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