Skip to main content
Glama
aws-cost-mcp

aws-cost-mcp

AWS cost anomalies

get_anomalies
Read-onlyIdempotent

Retrieves AWS cost anomalies ranked by impact, showing service, region, account, and usage type. Filters by date range and minimum impact to identify unexpected cloud spending.

Instructions

Recent cost anomalies flagged by AWS Cost Anomaly Detection, biggest impact first, with the service, region, account and usage type that caused each. Needs an anomaly monitor set up in the Billing console.

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": "get_anomalies"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoDay after the last day to look at, exclusive. Defaults to tomorrow (UTC).
startNoFirst day to look at, inclusive (YYYY-MM-DD). Defaults to 14 days ago.
formatNomarkdown: compact table for reading. json: structured data.markdown
minImpactNoIgnore anomalies whose total cost impact is below this amount.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, open-world behavior, so the bar is lower. The description adds genuinely new context beyond them: results are ordered by biggest impact first, each row identifies the responsible service/region/account/usage type, and the tool fails without a pre-configured anomaly monitor. It does not say what happens when no anomalies exist (empty vs error) or mention latency/cost of the query.

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?

Two tight sentences: what is returned and in what order, then the prerequisite. No filler, and the highest-value information (what the payload contains) is front-loaded.

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?

For a simple read-only list tool with no output schema, the description covers return contents, ordering, and the setup prerequisite. The only real gap is the empty-result behavior, which is minor here.

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%, so all four parameters (start, end, format, minImpact) are already fully documented, including defaults and the exclusive/inclusive boundary. The description adds no parameter-level detail beyond indirectly implying that ordering is by impact, which is not tunable. Baseline 3 applies.

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?

States a specific verb and resource ('Recent cost anomalies flagged by AWS Cost Anomaly Detection') plus the sort order and the dimensions carried per anomaly (service, region, account, usage type). An agent can distinguish this from get_cost_breakdown or get_forecast without inspecting the schema.

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?

Gives a clear usage condition and a hard prerequisite: an anomaly monitor must already exist in the Billing console. It does not explicitly say when to prefer this over compare_periods or get_cost_breakdown, so the alternative selection is left implicit.

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