get_ec2_metrics

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

With no annotations, the description carries the behavioral burden. It conveys a read-only retrieval from CloudWatch and correctly indicates the supported resource and time scope. It does not go into permissions, pagination, rate limits, or exact output shape, so it is adequate but not fully transparent.

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?

One clean sentence that front-loader the result type and resource before the time detail. There is no filler or unnecessary abstraction.

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 simple, two-parameter read-only tool with 100% schema coverage, the description is nearly complete. An agent can select and invoke it with confidence. Minor gaps are the lack of explicit sibling differentiation and no mention of response structure, but these are not critical given the clarity of the metric names.

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?

The input schema already documents both parameters completely, including default and max for periodMinutes. The description contributes contextual grouping of metrics (CPU, network) and the notion of a time window, but does not add parameter-level detail beyond the schema.

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 uses a specific verb, resource, and boundary: 'Get CloudWatch metrics (CPU, network) for an EC2 instance over a specified time period.' It clearly identifies what is returned and distinguishes it from sibling tools like get_ec2_health, get_ec2_instances, and get_app_metrics, even though no alternatives are named.

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 intended use is implied by the wording: when CloudWatch CPU/network metrics for a single EC2 instance over a time window are needed. However, it does not explicitly state when to prefer this over related siblings such as get_ec2_health, get_app_etrics, or get_database_metrics.

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