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

Annotations already provide readOnlyHint:true, idempotentHint:true, destructiveHint:false, so the safe read-only nature is covered. The description adds behavioral context beyond annotations: it mentions the `diagnostics` action bundles budget-loss as _campaign_budget_loss, explains why (budget is campaign-level), and specifies default data windows (last 7 days, top 50). This is additional transparency about data scope and bundling behavior, which is not in 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?

The description is dense and information-rich, but it is a single long paragraph with many nested parentheses and clauses, making it somewhat hard to parse. It front-loads the main purpose but becomes list-like in the middle. Although it's concise in word count relative to the scope, it could be better structured with bullet points or clearer separation of actions. Still, every sentence earns its place.

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?

Given the high complexity (9 parameters, 5 distinct actions, bulk support, no output schema), the description is remarkably complete. It covers scope (account + customer_id), time frames, filters, default limits, and answers common questions. It even explains the rationale for bundling budget loss. The lack of output schema is mitigated by detailed descriptions of what each action returns (e.g., approval_status, system_serving_status, Quality Score). Context is fully addressed.

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%, so the description must compensate for 9 parameters. It does by explaining that 'diagnostics' supports campaign_id/ad_group_id filters and days=7|14|30, and mentions bulk support for campaign_ids, ad_group_ids, customer_ids. However, it does not detail the exact meaning of 'account' vs 'customer_id' or 'query' (though query is for raw). Despite some gaps, it adds significant semantic value beyond the schema, which has no descriptions at all.

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 clearly identifies the tool as a combined diagnostics tool for Google Ads keywords, with a specific verb 'analytics' and distinct action modes (keywords, search_terms, status, diagnostics, raw). It explicitly names sibling tools (google_ads_keywords_keywords, google_ads_keywords_status, etc.) and differentiates by providing a unified interface, thus distinguishing from siblings.

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 description explicitly outlines when to use each action (e.g., 'status' answers 'why is my keyword not serving?', 'diagnostics' answers 'is it bid or Quality Score?') and mentions bulk support. It also indicates the `raw` action for any GAQL SELECT, and provides filters like days=7|14|30, which are clear usage guidelines. While it doesn't explicitly say 'when not to use', the action-specific guidance is strong enough.

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