Aws Capacity Forecast

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 real behavioral context beyond that: a 14-day lookback window, the exact metric and serverless variant used, severity thresholds, and the default fleet-wide region scope. It does not mention cost/latency or how far out forecasts are extrapolated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense, front-loaded, and free of filler — scope and method come first, thresholds follow. A few phrasings are telegraphic and partly redundant ('findings first ... soonest first'), which costs a little clarity for a reader without surrounding context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter read-only analysis tool with rich annotations and an output schema, the description supplies everything essential: what is computed, over what window, with what thresholds, and over what region scope. Return-value details are legitimately deferred to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With a single fully documented parameter, the schema baseline is high, but the description still adds meaning: it clarifies that omitting `region` evaluates all ELASTICACHE_REGIONS rather than a single region. This is useful, though it sits in slight tension with the schema text saying the parameter 'defaults to AWS_REGION', which an agent may find ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and output ('Days until memory is full across the fleet') plus the metric basis (DatabaseMemoryUsagePercentage, Serverless: BytesUsedForCache vs storage maximum), so an agent can tell this apart from generic metrics or inventory tools. It stops short of explicitly naming a sibling to contrast with, so it lands just under the top mark.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The thresholds ('Under 7 days critical, under 30 warning') imply a capacity-planning use case and give the agent a decision rule for interpreting results. However, there is no explicit statement of when to choose this over alternatives like aws_metrics, aws_scale_readiness, or aws_triage, and no exclusion criteria.

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