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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, so safety is covered and the description adds useful non-obvious behavior: money is returned in the account currency, defaults are last 30 days and top 25 by cost, and each level surfaces its own column set (all conversions, bid estimates, match type, average CPC). It does not disclose pagination/row-cap behavior beyond the default, how truncation is signalled, or what the render modes produce.

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 capability and supported levels are front-loaded, followed by metric content, currency, defaults, and the read-only note — a sensible information order with no filler sentences. The trailing 'Tools revision: d80f65c0.' is metadata noise that does not help an agent decide or invoke, and the level enumeration could be compressed.

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, the description need not explain return values, and it does enough for a read-only reporting tool. However, for a 10-parameter tool with zero schema descriptions, an agent still cannot infer what render controls, what include_removed does to results, or whether campaign_id/ad_group_id scope or are required for certain levels — gaps that affect correct invocation.

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 0% across 10 parameters, so the description has to carry the load. It adds real meaning for level (enumerated granularities), start_date/end_date (30-day default), and max_rows (25 default), but is silent on render, include_removed, customer_id, campaign_id, ad_group_id, and only obliquely hints at extra_metrics via the 'each level's own columns' phrasing. Roughly half the surface remains undocumented in both schema and description.

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 opens with a specific verb and resource ('Report Google Ads performance') and enumerates every supported level (account, campaign, ad group, ad, keyword, search term, portfolio bid strategy), which maps directly onto the level enum. It is clearly distinguishable from write tools in the sibling list, but it never distinguishes itself from analytics siblings such as analyze_search_terms, analyze_waste, or day_of_week that could plausibly overlap.

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 only implied: the level list tells the agent what granularity it can request, and 'Default: last 30 days, top 25 by cost' tells it what happens if it says nothing. There is no explicit when-to-use statement, no when-not-to-use, and no routing to an alternative tool when a different question (waste analysis, search-term intent) is being asked.

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