google_ads_cost_increase_investigate

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

With no annotations, the description carries the full burden and does so well: it declares read-only behavior, the hardcoded LAST_7_DAYS window, per-section caps (top 20 search terms, up to 10 bid/budget events, up to 10 negative keyword candidates), and critically that any failing subcomponent returns null instead of aborting the call. It doesn't cover rate limits, latency, or account-permission requirements, which keeps it short of 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?

Front-loaded with the purpose and comparison window before the long return-shape enumeration, which is justified by the absence of an output schema. The inline field list is dense but each item earns its place; it's slightly overlong as a single paragraph, but no sentence is filler.

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 composite diagnostic tool with no output schema and no annotations, the description covers purpose, time window, return structure, degradation behavior, and sibling alternatives. An agent can decide to call it, know what it will receive, and know how failures manifest without opening anything else.

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%, and both parameters already document format, fallback behavior, and how to obtain the campaign_id. The description adds no parameter-level detail beyond implying the comparison is scoped to a campaign. Baseline 3 applies since the schema does the work.

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?

States a specific verb and resource ('Investigate the root cause of a Google Ads cost spike or CPA deterioration') plus the exact analytical framing (last 7 days vs prior 7 days). This is unmistakably distinct from sibling read/report tools such as google_ads_performance_report or google_ads_cpc_detect_trend.

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?

Explicitly routes the agent: 'For a broader diagnostic composite use google_ads_performance_analyze; for CPA-vs-target monitoring use google_ads_monitoring_cpa_goal.' It also states the triggering symptom (cost spike or CPA deterioration), so when-to-use and alternatives are both covered.

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