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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), so the bar is lower; the description nonetheless adds two real behavioral facts: results are denominated in the account currency, and near-exact deduplication may drop inputs so the response may not map 1:1 to the request. It omits any mention of the per-call input caps (20 keywords, 10 geo targets) that are only visible in the schema.

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?

A single tightly written sentence with the operation and its two most important caveats front-loaded and no filler. Every clause carries information.

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 carries the burden of explaining what 'historical metrics' actually returns (volume, competition, bid ranges, time window), and it does not. It also leaves the nested body parameters and their limits undocumented, which is thin for a 3-parameter tool with a nested object.

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 only 33% (only customer_id is documented), and the nested body fields keywords, language_id, and geo_target_ids carry no descriptions at all. The description adds no parameter meaning beyond the currency note, so it fails to compensate for the coverage gap.

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 (Read) and resource (keyword historical metrics) plus a scope qualifier (bounded, account currency), so an agent knows it is a read of historical performance data. It does not, however, differentiate itself from nearby siblings such as google_ads_keyword_forecast_metrics, google_ads_keyword_ideas_generate, or google_ads_benchmark_metrics, leaving the agent to infer the boundary.

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?

There is no when-to-use guidance and no named alternative, despite several plausible siblings (forecast metrics, ideas generate, trending topics) that could be confused with it. The only implicit cue is 'historical' vs. future-facing tools, which the agent must derive on its own.

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