Ads report with True ROAS

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

Annotations already declare it a safe read (readOnlyHint true, destructiveHint false, openWorldHint true), and the description adds real substance on top: app-side figures come back null with a reason when currencies differ or tracking is too new, amounts are returned in the currency named in the answer, and an API key is required for a preview endpoint. That covers data-quality edge cases and auth needs beyond the annotations. It does not discuss volume limits or call cost, which keeps it from a 5.

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?

Four short sentences, front-loaded with the output shape before the caveats and the error contract. Every sentence carries information an agent would otherwise have to discover by trial: null semantics, currency behavior, auth requirement, and the no-fabrication rule.

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?

With no output schema, the description does the work of describing the return shape (per campaign, per day, True ROAS, null-with-reason, currency of amounts), which is exactly what an agent needs before calling. Combined with the annotations covering the safety profile and the explicit failure contract, the definition is broadly sufficient. The remaining shortfall is that it never explains the windowing parameters or the basis choice, which materially affect the numbers returned.

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 80%, above the threshold where the schema is expected to carry parameter meaning, and the description's 'per campaign and per day' phrasing adds interpretable context for the date and view windows. It still says nothing about the basis enum (ad_event_time vs conversion_time), which is the one parameter the schema leaves undocumented and the one with genuine semantic weight. That gap holds it below a 5 despite the strong baseline.

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 granularity: campaign-level and day-level totals paired with True ROAS derived from the store's own Shopify orders. It also identifies the backing service (Avada ChatGPT Ads) and that this is a preview API. It stops short of contrasting itself with the closest siblings such as measurement_get_ads_breakdown or measurement_get_product_report, so differentiation is left to the agent.

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?

Usage is implied by the granularity statement (campaign-and-day ROAS reporting), and there is explicit guidance for the failure path: if the tool answers unavailable, relay the reason and steps and never invent or zero-fill numbers. However, there is no guidance on when to pick this over the breakdown, overview, or product report siblings, and no stated preconditions such as needing campaign data to exist first.

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