Skip to main content
Glama
platypus-db

platypus-db

Official

profile_table

Profiles a table or view from sampled rows to report nulls, distinct values, ranges, frequent values, patterns, and numeric spread, with counts only for sensitive columns.

Instructions

Profiles the columns of a table or view from a sample of its rows (the first sample_rows, default 10000, up to 100000; no order is implied): per column NULLs, distinct values, empty texts, minimum and maximum, the most frequent values, patterns (emails, dates, numbers stored as text...) and, for numbers, their spread. Sensitive columns (as in results) give counts only: no value of any kind. Read-only, within the connection's limits; max_bytes and timeout_seconds work as in run_query.

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": {
      "connection": "<connection>",
      "schema": "<schema>",
      "table": "<table>"
    },
    "name": "profile_table"
  }
}

Input Schema

NameRequiredDescriptionDefault
tableYesThe table, view or collection.
schemaYesThe table's schema (a database in MySQL and MongoDB, `main` in SQLite and DuckDB).
max_bytesNoBytes of output at most (default 32768, up to 1048576).
connectionYesThe connection's name, as `list_connections` shows it.
sample_rowsNoRows to profile: the first ones the database reads (default 10000, up to 100000).
timeout_secondsNoSeconds the read may take before it is cancelled (default 30, up to 300).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.2

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it declares read-only behavior, that sampling is the first N rows with no ordering implied, that sensitive columns yield counts only and no values, and that connection limits and timeout apply. It does not cover error modes or what happens on cancellation, so it stops 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose and the output inventory, then sampling semantics, then safety and limits. Dense but every clause carries information; the long parenthetical list makes it a single heavy paragraph, which is a minor readability cost.

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?

For a six-parameter analytic tool with no output schema, the description covers what gets computed, how rows are sampled, how sensitive data is handled, and how limits behave. Remaining gaps (error behavior, response shape/volume) are minor given the explicit result inventory.

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 description coverage is 100%, so baseline is 3, but the description adds real meaning: sample_rows is explicitly the first rows the database reads with no order implied, and max_bytes/timeout_seconds are anchored to run_query's semantics rather than restated.

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?

States a specific verb and resource ('Profiles the columns of a table or view from a sample of its rows') and enumerates the produced statistics, so an agent can distinguish it from a pure schema tool like describe_table. It stops short of naming a sibling or stating exclusion explicitly, so it is clear but not maximally differentiated.

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 implied by the output inventory (data profiling vs. schema description) and by the note that sensitive columns return counts only, but there is no explicit 'use this when / use describe_table or run_query instead' guidance. An agent can infer the right context but is not told the boundaries.

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