mcp-elasticache-ops

Overview Schema Source Related Servers Discussions Admin

Node Cluster Keyspace Sample

node_cluster_keyspace_sample

Read-onlyIdempotent

Samples keys across all shard primaries to detect keyspace skew, report per-shard status, and surface dead shards without failing.

Instructions

node_keyspace_sample on every shard primary: keys merged with a shard label, per-shard status, skew findings. A dead shard is reported, never fatal. Budget and sample split across primaries.

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": "node_cluster_keyspace_sample"
  }
}

Input Schema

Name	Required	Description
`top`	No
`match`	No	SCAN MATCH glob, e.g. 'session:*'
`pause_ms`	No	Sleep between SCAN batches
`scan_count`	No	SCAN COUNT hint
`max_seconds`	No	Total wall-clock budget, split across primaries
`max_workers`	No	Concurrent shard samplers
`sample_size`	No	Max keys to inspect, split across primaries
`top_prefixes`	No	Key prefixes to report
`per_node_timeout`	No	Extra seconds to wait for a stuck shard

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 12, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/open-world, so the description is not needed for safety. It does add real behavioral context beyond them: partial-failure semantics ('a dead shard is reported, never fatal'), merged output carrying a `shard` label, per-shard status plus skew findings, and that budget and sample are divided across primaries.

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?

Three short sentences, front-loaded with the core fan-out behavior and no filler. The telegraphic first clause ('node_keyspace_sample on every shard primary:') is slightly compressed but still parseable.

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 detail is unnecessary, and annotations cover the safety profile. The description covers fan-out scope, partial failure, and result shape well; the only gap is guidance on when to prefer the single-node sampler or avoid a cluster-wide scan.

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 coverage is 89%, so the schema already documents all nine parameters, including that max_seconds and sample_size are 'split across primaries'. The description restates that split behavior but adds no new parameter detail (e.g., how per_node_timeout interacts with a stuck shard, or how max_workers affects the split).

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 concrete verb and scope: it runs node_keyspace_sample 'on every shard primary' and merges keys with a `shard` label. That framing implicitly separates it from the single-node sibling node_keyspace_sample, though it never names that sibling as the non-cluster alternative.

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?

Use on a cluster (all shard primaries) versus a single node is implied by 'on every shard primary', which is the main selection cue. There is no explicit when-not guidance, no statement about cost/latency tradeoffs of fanning out, and no named alternative.

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

Deploy Server