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

With no annotations, the description carries the full behavioral burden. It usefully discloses that prices are on-demand only, cover 21 regions, and support Linux or Windows, but it omits data freshness, whether the limit parameter paginates or truncates results, and whether hourly and monthly values are both always returned.

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?

A single dense sentence with the primary purpose front-loaded, followed by the two query modes and OS options. Every clause adds useful information, and there is no filler or repetition.

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?

The output schema covers return values, and the description adequately explains the core query modes and most parameters. However, for a 7-parameter tool with no annotation coverage, remaining gaps around the limit parameter, region defaults, and the distinction between hourly and monthly results leave it short of fully complete.

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?

Schema coverage is 0%, so the description must compensate, and it largely does: it explains the OS choice, the two lookup modes, minimum vCPU and memory constraints, and gives family examples such as GPU, m7i, and Compute optimized. The only clear gap is the limit parameter, whose behavior is not described anywhere.

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?

States a specific resource (AWS EC2 on-demand hourly and monthly prices), a concrete scope (21 regions), and clearly distinguishes itself from siblings like azure_vm_prices by naming the cloud provider and pricing model. An agent can tell exactly what data this tool returns.

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 description implies two query modes (one instance type, or cheapest types matching constraints), which gives some usage context. However, it does not say when to use this tool versus alternatives such as gpu_rental_prices or azure_vm_prices, nor does it explain tradeoffs between specifying an instance type versus using filters.

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