Skip to main content
Glama

Profile Named Local IBGE Parquet Views

ibge_microdata_profile_parquet_views
Read-onlyIdempotent

Profile local Parquet files as DuckDB views for bounded exploratory statistics. Get row counts, column types, null counts, numeric summaries, and frequent values without custom SQL.

Instructions

Profile local Parquet files as named DuckDB views and return bounded exploratory statistics.

Use this after converting IBGE fixed-width microdata to Parquet and before writing custom SQL. The tool reports row counts, column types, null/non-null counts, optional numeric min/max/mean, frequent values, and optional sample rows. By default it profiles the first 25 columns to keep exploration bounded; pass columns for a precise subset.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topKNoNumber of most frequent values to return per profiled column. Defaults to 5 and is capped at 50.
viewsYesNamed local Parquet views to profile.
columnsNoOptional specific column names to profile. If omitted, the first maxColumns columns are profiled.
maxColumnsNoMaximum columns to profile when columns is omitted. Defaults to 25 and is capped at 200.
sampleRowsNoNumber of sample rows to return per view. Defaults to 0 and is capped at 100.
Behavior4/5

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

Adds detail beyond annotations by listing reported statistics (row counts, column types, null/non-null counts, optional numeric summaries, frequent values, sample rows) and mentions bounded exploration. No contradiction with annotations.

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?

Two short paragraphs, four sentences total. Every sentence adds value: first defines purpose and output, second gives usage guidance and defaults. No redundancy.

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?

Covers purpose, output components, usage timing, default behavior, and options. Could be more complete by describing the return format explicitly, but given no output schema, the description is fairly comprehensive.

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%, so baseline is 3. Description provides no additional param-specific details beyond schema descriptions; it reiterates overall behavior but does not enrich parameter understanding.

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?

Description clearly states the tool profiles local Parquet files as DuckDB views and returns bounded exploratory statistics. It distinguishes from sibling tools like query or describe by specifying the context 'after converting... and before writing custom SQL'.

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?

Directly advises 'Use this after converting IBGE fixed-width microdata to Parquet and before writing custom SQL.' Also explains default column behavior and alternative to pass specific columns. However, it does not explicitly mention when not to use or name alternative tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/emmanueltsallis/ibge-microdata-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server