StatsPAI

describe_data

Read-only

Profiles a dataset from a path, handle or inline table, returning shape, dtypes, missing counts, head rows and numeric summaries, plus the transform lineage behind a data handle.

Instructions

Profile a dataset (data_id, data_path or inline data): shape, dtypes, missing counts, head, numeric summary and -- for a handle -- the lineage of transforms that produced it.

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": "describe_data"
  }
}

Input Schema

Name	Required	Description	Default
`head`	No	Rows to echo.
`detail`	No	Payload depth; agent is the fullest.	agent
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`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

A4/5.0

Behavior4/5

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 behavioral context by naming exactly what the profile contains and clarifying that lineage is only returned for handle-based inputs. It does not mention the as_handle/result_id caching path or output truncation, so it falls short of 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?

A single front-loaded sentence with the verb and resource first, a compact input-mode parenthetical, and the conditional lineage clause at the end. No filler and no redundancy with the schema.

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?

With 11 optional parameters, 100% schema coverage, an output schema and read-only annotations, the description carries enough to call the tool correctly. The main omission is the as_handle/result_id fit-caching flow, which an agent would only learn from the schema.

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 every one of the 11 parameters is already documented in the schema. The description restates the three input-mode parameters but adds no interpretation (e.g. precedence between data_id and data_path, or what 'detail' levels change) beyond the schema, so baseline 3 applies.

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?

States a specific verb ('Profile') and resource ('a dataset'), then enumerates the concrete outputs (shape, dtypes, missing counts, head, numeric summary, lineage). This is clearly distinct from data-movement siblings like load_data and transform_data.

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

Usage Guidelines3/5

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

The parenthetical lists the three accepted input modes (data_id, data_path, inline data), which implicitly guides input selection, and the '-- for a handle --' clause conditions when lineage is included. However, there is no explicit when-to-use vs alternatives such as describe_function or audit, and no exclusions.

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