Skip to main content
Glama

profile_dataset

Read-only

Profiles a CSV dataset by returning row and column counts plus per-column inferred type, missing percentage, unique count, and example values.

Instructions

Profile a dataset: rows, columns, and per column the inferred type, missing %, unique count and example values.

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": {
      "name": "<name>"
    },
    "name": "profile_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description does not contradict it. The description adds useful context about what the profile output contains, but says nothing about cost, runtime, or behavior on very large datasets. The existence of an output schema means it need not describe return values in detail.

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 that names the action first and then lists the computed outputs in a compact clause. There is no filler, hedging, or repetition, and it reads clearly despite the dense enumeration of profile fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because an output schema exists, return values need not be explained, and the annotations carry the safety profile, so the core is covered. What is missing is how the dataset is identified by the single parameter and any limits on dataset size or runtime, which matters for a profiling operation that may scan whole tables.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the sole parameter, "name", is an undescribed string. The description never clarifies whether that is a dataset name, identifier, path, or table reference, so it adds no meaning beyond the bare schema. For a one-parameter tool this is a real gap rather than a minor one.

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?

The description states a specific verb and resource ("Profile a dataset") and enumerates exactly what the profile contains: row/column counts plus per-column type, missing %, unique count, and example values. That clearly separates it from list_datasets and preview_rows, though it never names an alternative such as quality_score, which could overlap with the statistical summary it produces.

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?

Usage is only implied: an agent can infer that this produces a summary for a named dataset rather than returning rows, but there is no explicit when-to-use/when-not guidance and no mention of when quality_score or suggest_cleaning would be the better pick. Adequate but leaves routing to the sibling tools unstated.

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