Skip to main content
Glama

Analyze Schema Normalization

analyze_schema_normalization
Read-onlyIdempotent

Review keys, foreign keys, indexes, and sampled list-like columns to detect likely normal-form problems in a database schema before refactoring.

Instructions

Review keys, foreign keys, indexes and sampled list-like columns for likely normal-form problems.

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": "analyze_schema_normalization"
  }
}

Input Schema

NameRequiredDescriptionDefault
jdbc_urlNoOptional JDBC URL to target a specific database (credentials embedded in URL); uses environment default when omitted
sample_rowsNoRows sampled per list-like column (default 20, 0 disables sampling)
default_tableNoTable used for dependency lines without a 'table:' prefix
include_samplesNoSample list-like columns to find delimited values (default true)
functional_dependenciesNoOptional newline-separated functional dependencies, e.g. 'orders: customer_id -> customer_name'. Analysis uses only these declarations; nothing is inferred from data.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.1
    • addedInput schema / properties / jdbc_url
      Added value: +{
      +  "description": "Optional JDBC URL to target a specific database (credentials embedded in URL); uses environment default when omitted",
      +  "type": "string"
      +}
  2. First observedv1.0.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description is free to add method-level context, and it does: it discloses that list-like columns are sampled and that dependency analysis uses only explicitly declared FDs with nothing inferred from data. That last constraint materially changes how an agent should prepare inputs. It omits that the tool touches a live database via the environment default connection, which matters for an openWorld tool.

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 no filler, and the scope enumeration is packed efficiently into one clause. Nothing is repeated from the title or annotations.

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?

All parameters are documented and safety is covered by annotations, but with no output schema the description never says what the tool returns, e.g. a findings list of normal-form violations versus raw key metadata. It also leaves implicit that a live database connection is used by default, which is significant given openWorldHint=true.

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%, with each of the five parameters self-documenting including defaults and the meaning of sample_rows=0. The description reinforces the sampling concept through 'sampled list-like columns' but adds no format or syntax detail beyond what the schema already states, so the baseline of 3 applies.

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 names a specific action (review for likely normal-form problems) and enumerates the artifacts inspected: keys, foreign keys, indexes, and sampled list-like columns. An agent can immediately tell this is a normalization audit rather than a generic schema dump. It stops short of distinguishing itself from related siblings such as export_schema_ddl or describe_table, which are nearby in the catalog.

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 by the scope statement; there is no explicit 'use this when' condition, no exclusion such as 'not for DDL export', and no named alternative among the schema-oriented siblings. The note that functional dependency analysis uses only declared dependencies hints at how to use it, but not when to choose it over another tool.

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