Skip to main content
Glama
Sign In
mcp-elasticache-ops

mcp-elasticache-ops

by ritojoao
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Aws Shard Balance

aws_shard_balance
Read-onlyIdempotent

Detect ElastiCache shard skew from CloudWatch alone, flagging hot shards, memory imbalance, and pinned primaries to diagnose replication-group issues without a data-plane connection.

Instructions

Per-shard skew from CloudWatch only (no data-plane connection). Findings first: hot shard (over 2x the median and above 50% CPU), memory skew, one primary pinned near 100% CPU (hot-key signature).

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": {
      "replication_group_id": "<replication_group_id>"
    },
    "name": "aws_shard_balance"
  }
}

Input Schema

NameRequiredDescriptionDefault
regionNoAWS region; defaults to AWS_REGION
minutesNoCloudWatch window in minutes
replication_group_idYesReplicationGroupId to check for shard skew

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

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 (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description is free to add substance — and it does, disclosing the exact detection thresholds (2x median, 50% CPU, pinned primary) and the data source limitation. That tells an agent what the tool will and will not see, which annotations cannot. It loses a point for not stating how the 'no data-plane' constraint affects confidence or what happens when CloudWatch data is sparse.

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?

Two compact sentences with the source constraint in the leading clause and the findings enumerated after, so the loudest information arrives first. The telegraphic phrasing ('Findings first:', 'hot-key signature') is dense but not padded — every clause carries an evaluable fact.

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?

An output schema exists, so return-value explanation is unnecessary, and the description correctly spends its budget on detection thresholds and data-source scope instead. What remains uncovered is edge behavior for a 5-minute window or a replication group with no CloudWatch data, a minor gap for a read-only diagnostic.

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%: region (defaults to AWS_REGION), minutes (CloudWatch window, 5–20160), and replication_group_id are all documented in the schema. The description adds no parameter-level meaning beyond that baseline, so a 3 is the correct resting score.

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 states a specific verb+resource pair: per-shard skew analysis for an ElastiCache replication group, sourced exclusively from CloudWatch. It names the concrete skew signals detected (hot shard over 2x median and above 50% CPU, memory skew, a primary pinned near 100% CPU as a hot-key signature). It falls short of a 5 because it never names a sibling it is not (e.g. aws_metrics or aws_replication_group_audit), so differentiation is inferred from the signal list 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 Guidelines3/5

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

The parenthetical '(no data-plane connection)' implies a boundary: this is a control-plane/CloudWatch-only view, so agents needing live engine metrics must look elsewhere. However, it never explicitly says when to choose this over aws_metrics or aws_replication_group_audit. Usage is implied by the signal list, not routed.

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

Deploy Server

Other Tools