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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: spend is reported in both the ad account's own currency and USD, metric provenance is disclosed (Apple counts each download while Google's installs are whatever Google reports), and it explicitly states that suggested next steps are 'never done for the person' — a meaningful guarantee that the tool will not act.

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?

It is front-loaded with the usage trigger, which is good, but the remainder is a single run-on sentence enumerating roughly ten disjoint capabilities. The list does earn some of its length by clarifying scope, yet phrases like 'what it brought' and the parenthetical about Google's installs make it harder to scan than a short structured breakdown would.

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 an output schema present, return-shape explanation is unnecessary, and both parameters are fully documented in the schema. Coverage of metrics, currencies, and the no-side-effects guarantee is good. Minor gap: nothing says what happens when no ad account is linked or when one platform has no data, which an agent would want before calling.

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 100% with only two parameters, and the period parameter's full syntax (7d, 30d, 12m, explicit dates, ranges) is already documented in the schema. The description implies date-bounded reporting through 'ran when' but adds no format or defaulting detail beyond the schema, so the baseline of 3 applies.

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 scope is specific: paid advertising across Apple Ads and Google Ads, with an enumeration of the data returned (campaigns, spend in two currencies, downloads/installs, cost per download, payback, changes, search terms). It is distinguishable from siblings like timeline or why_did_it_change because it names the ad-account domain explicitly, though the phrase 'use for anything about paid ads' is a use case rather than a verb+resource formulation.

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 opening clause 'Use for anything about paid ads' gives a positive trigger condition, which is genuinely helpful. However, there is no when-not guidance and no routing to alternatives, despite siblings like why_did_it_change and timeline that plausibly overlap when the question is 'why did installs move' and ads are only one contributing factor.

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