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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's "Read-only" line is confirmatory rather than additive. It earns credit elsewhere: it discloses that results are rendered to the user as a visual dashboard card, that automatic insights are appended, and that amounts are returned in each account's own currency — all behavior an agent could not infer from the annotations.

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?

Three sentences, front-loaded with the trigger and the returned fields, with defaults and currency notes trailing where they belong. The metrics enumeration is long but each term is signal; nothing is filler, though the sentence is dense enough to be worth splitting.

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 must describe returns itself, and it does — metrics, period-over-period change, daily trend, per-campaign table and insights. Combined with the default period and currency note, this is close to complete for a 9-parameter read-only reporting tool; the remaining gap is guidance on account vs folder selection across multiple accounts.

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 100%, so every parameter already has its own description and the baseline is 3. The description restates the level behavior (per-campaign table vs per ad group with level=ad_group) and the 30-day default, but adds no syntax, precedence or interaction detail beyond the schema — notably it is silent on how folder, account and multiple accounts interact.

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?

A specific verb-plus-resource statement ("how their Google Ads account or campaigns are performing") followed by an explicit list of returned metrics (spend, conversions, CPA, clicks, CTR, CPC, conversion value, ROAS). It is clear what the tool produces, but it never distinguishes itself from close siblings such as google_ads_ad_performance, google_ads_breakdown or google_ads_conversion_performance.

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 sentence gives an explicit trigger condition (the user asks about Google Ads performance), and the description carries a default period and a summary/full sizing cue. What is missing is any exclusion or routing advice — an agent cannot tell from this text when to choose google_ads_breakdown or google_ads_ad_performance instead.

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