Skip to main content
Glama
pg-perf-mcp

pg-perf-mcp

by dixitgurv

table_health

List large PostgreSQL tables by sequential-to-index scan ratio, dead tuple share, and last vacuum/analyze time to identify maintenance issues and prioritize cleanup.

Instructions

Largest tables with seq-vs-index scan ratio, dead tuple share and last vacuum/analyze.

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": "table_health"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.7/5.0
Behavior2/5

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

No annotations exist, so the description carries the full behavioral burden. It enumerates the metrics but says nothing about read-only semantics, cost/heaviness of scanning catalog stats, ordering of results, or how staleness of vacuum/analyze timestamps is reported; almost all of its content is return-value material that the output schema already covers.

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?

A single compact sentence with no filler and the key dimensions front-loaded. It is efficient, though its terseness leaves terms like 'seq-vs-index scan ratio' and 'dead tuple share' unelaborated.

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

Completeness2/5

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

With an output schema present, return-value explanation is not required, yet the description offers little else: no parameter meaning, no usage context, and no behavioral notes for a no-annotation tool. It is too thin for a diagnostic tool whose invocation criteria are non-obvious.

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% for the single 'limit' parameter (title and default 20 only). The description never mentions limit, so an agent cannot tell whether it caps the number of tables returned or affects ordering; it fails to compensate for the coverage gap.

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 concrete, specific resources/metrics — largest tables, seq-vs-index scan ratio, dead tuple share, last vacuum/analyze — which distinguishes it from siblings like slow_queries or unused_indexes. It lacks an explicit verb (list/report) and reads as a noun phrase, so what the tool actually does is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites (e.g., stats collector, permissions on pg_stat views), and no routing to alternatives such as database_overview or unused_indexes. The agent must infer the diagnostic scenario entirely from the metric list.

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