get_keyword_forecasts

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

No annotations are present, so the description carries full burden. It discloses null impressions and absent estimates, preservation of zero/fractional clicks, strict date parsing, February 29 clamping, account time zone refusal, decimal currency, and side-effect-free computation—exceptionally 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?

The description is dense but every sentence carries a substantive constraint or behavior; the main action is front-loaded. It would be more skimmable with bullets, but no filler is present.

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?

Given no output schema and no annotations, the description covers input constraints, output nullability and numeric preservation, currency, and side effects. The only minor gap, explicit customer_id roles, is arguably covered by 'requested account's time zone.'

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%, but the description compensates well by explaining date-range semantics, the keyword_texts alias and agreement rule, and monetary output format. It leaves customer_id largely implicit, so it is not a perfect 5.

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?

Opens with a specific verb and resource: 'Forecast clicks, cost, and average CPC for supplied keywords.' It then distinguishes itself by noting the nonpersisting v25 API and explicitly 'no KeywordPlan is ever created,' which separates it from sibling planning and reporting 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?

Clear context is given: this is for forecasting future date ranges, with start must be future and end within one calendar year, and defaults to next 30 account-local days. It does not explicitly name alternative tools or give when-not-to-use conditions, so it misses the top bar but is more than merely implied.

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