get_cost_forecast

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

With no annotations, the description carries the behavioral burden. It clearly states that the tool returns a mean forecast plus an 80% prediction interval, which sets expectations about results and implies a read-only forecasting operation. Additional error or edge-case behavior is not disclosed, but the core output behavior is well covered.

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?

The description is compact, clearly worded, and front-loaded. Every sentence adds value — first the action and date constraint, then the exact shape of the forecast output. No wasted words or irrelevant background.

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 forecast tool with a small parameter set, the description adequately explains the main purpose, expected result, and important date caveat. It lacks deeper detail on unusual inputs or failure behavior, but the essential information for selecting and simple invocation is present.

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 description coverage is only 60%, and the tool description does not compensate: it restates the start-date constraint already present in the schema but gives no added meaning for metric, granularity, or the filter object. The description names no metrics, default choices, or range semantics beyond what the schema already provides.

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 and resource: 'Forecast future AWS spend for the account over a date range' — which clearly identifies the action and target. It also names the output type (mean forecast plus 80% prediction interval), making the tool easy to distinguish from cost/usage retrieval tools.

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 instruction 'must start today or later' establishes a clear constraint and scenario for when this tool should be used. It does not explicitly mention alternatives like get_cost_and_usage for historical spend, but the future-focused wording makes the intended context fairly obvious.

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