Skip to main content
Glama
aws-cost-mcp

aws-cost-mcp

AWS cost breakdown

get_cost_breakdown
Read-onlyIdempotent

Break down AWS costs by service, account, region, usage type, or cost allocation tag for a date range, returning top groups sorted by cost and collapsing the rest into Others.

Instructions

AWS cost for a date range, grouped by service, account, region, usage type or cost allocation tag. Defaults to month-to-date by service. Returns the top groups sorted by cost, with the rest collapsed into 'Others'.

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_cost_breakdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoDay after the last day of the range, exclusive (YYYY-MM-DD). At most tomorrow (UTC).
startNoFirst day of the range, inclusive (YYYY-MM-DD). Omit with `end` for month-to-date.
formatNomarkdown: compact table for reading. json: structured data.markdown
metricNoCost metric. Use AmortizedCost to spread Savings Plans / RI upfront fees.UnblendedCost
tagKeyNoCost allocation tag key to group by, e.g. `team`. Only with groupBy TAG.
groupByNoWhat to break the cost down by. TAG requires `tagKey`.SERVICE
granularityNoDAILY adds a per-day total table; MONTHLY is cheaper on context.MONTHLY

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered. The description adds genuinely new behavior: results are sorted by cost, truncated to the top groups, and the remainder is collapsed into 'Others' — the key output-shaping behavior an agent needs and which no output schema supplies.

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?

Three compact sentences: what it returns, what the defaults are, and how the result is shaped. No filler, and the resource and grouping dimensions are 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?

With no output schema, the description carries the return-shape burden and does disclose sorting and 'Others' collapsing, which is the most important detail. It omits how many groups constitute 'top' before collapsing, a gap an agent cannot resolve from the structured fields.

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% and includes enum semantics and a per-parameter note, e.g. AmortizedCost for spreading Savings Plans/RI fees and TAG requiring tagKey. The description only restates the default groupBy and date-range behavior already documented in the schema, adding no new parameter meaning.

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?

States a specific verb and resource ('AWS cost for a date range') plus the dimensions it can be grouped by, which is concrete enough to act on without opening the schema. It does not name or contrast against siblings such as compare_periods or get_forecast, so an agent must infer the boundary itself.

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?

Usage is only implied via the stated defaults ('Defaults to month-to-date by service'), which tells an agent the zero-argument behavior but not when to prefer compare_periods, get_forecast, or get_anomalies instead. No when-not guidance or prerequisites are given.

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