Skip to main content
Glama
devopam

MCPg - Production-grade PostgreSQL MCP Server

Recommend redistribute

recommend_redistribute
Read-only

Diagnoses distribution skew in hash-distributed tables by analyzing column cardinality. Suggests an improved distribution key and generates ALTER TABLE DDL for rebalancing.

Instructions

Distribution-skew advisor for a hash-distributed table. Reads pg_stats.n_distinct for every column on the table and suggests a better hash key when the current one is low-cardinality. Pure catalog read — no per-segment scans. Returns ranked candidates, optional recommendation, and ready-to-review suggested_ddl (ALTER TABLE … SET WITH (REORGANIZE=TRUE) DISTRIBUTED BY (col)). Diagnosis-only — never executes. On vanilla PG returns available=false.

Example: recommend_redistribute(schema='public', table='fact_sales')

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tableYes
schemaYes
databaseNoOptional: target a configured secondary (read-only) database by name; omit for the primary. Call list_databases to see the configured ids.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
tableYes
detailYes
schemaYes
availableYes
candidatesYes
suggested_ddlYes
current_methodYes
recommendationYes
current_columnsYes
Behavior5/5

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

The description adds significant behavioral context beyond annotations: it confirms 'pure catalog read', 'no per-segment scans', 'diagnosis-only', and behavior on vanilla PG. No contradiction with readOnlyHint=true.

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?

The description is concise (5 sentences) with an example, front-loaded with the core concept, and no unnecessary words.

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?

Given the output schema exists, the description adequately covers return values and edge cases. However, it could mention the optional database parameter for completeness.

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?

Only 33% of parameters have descriptions in the schema; the description provides an example call but does not detail each parameter's semantics, leaving the optional database parameter under-explained.

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?

The description specifies the tool is a distribution-skew advisor for hash-distributed tables, detailing its functionality (reads n_distinct, suggests better hash key) and distinguishing it from sibling tools like recommend_indexes or recommend_skip_scan_indexes.

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?

The description clearly states it is diagnosis-only and never executes, and mentions behavior on vanilla PG, but does not explicitly contrast with alternative tools for distribution analysis or specify when not to use it.

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/devopam/MCPg'

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