Skip to main content
Glama
aws-cost-mcp

aws-cost-mcp

AWS cost forecast

get_forecast
Read-onlyIdempotent

Forecast AWS spend for the remaining days until month-end or a custom date to plan upcoming costs; pair with cost breakdowns for spend already incurred.

Instructions

Forecast AWS spend from today until the end of the month (or a custom end date). Covers only the remaining days; combine with get_cost_breakdown for spend already incurred.

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_forecast"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoDay after the last day to forecast, exclusive (YYYY-MM-DD). Defaults to the end of the current month. Must be after today (UTC).
formatNomarkdown: compact table for reading. json: structured data.markdown
metricNoCost metric. Use AmortizedCost to spread Savings Plans / RI upfront fees.UnblendedCost
granularityNoDAILY adds a per-day table; MONTHLY is cheaper on context.MONTHLY

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description's added value is the scope constraint (future-only, remaining days) and the end-of-month default horizon, which is genuinely useful. It says nothing about forecast availability depending on Cost Explorer being enabled, or about confidence/accuracy of projections — the main behavioral traits an agent cannot infer from annotations.

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 sentences, no filler, with the coverage constraint front-loaded before the sibling reference. Every clause carries information the agent needs.

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 zero-required-parameter read tool with full schema coverage and annotations, the definition covers purpose, scope and cross-tool usage. The remaining gap is that no output schema exists and the description never sketches the return shape (a single projected total versus a daily series), leaving the agent to infer it from the granularity and format parameters.

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 every parameter, enum and default is documented in the schema, so the baseline is 3. The description only gestures at the "custom end date" via its mention of an alternate horizon; it adds no meaning beyond the schema for metric, granularity or format.

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?

Names a specific verb and resource ("Forecast AWS spend") plus a precise time scope ("from today until the end of the month"), and explicitly restricts scope to "only the remaining days." That scope statement is what separates it from get_cost_breakdown, so an agent can route between the two without opening a 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 an explicit pairing rule: combine with get_cost_breakdown for spend already incurred, which tells the agent when this tool alone is insufficient. It stops short of naming when-not-to-use-this-at-all cases (e.g., historical windows), but the forward-only scope implies them.

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