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

With no annotations, the description carries the full behavioral burden and does so thoroughly: cache-first with auto-refresh, previous-period comparison, only entities with impressions appearing, PMax lacking ad groups/keywords, Search-network-only competitive metrics reading 0 elsewhere, search_lost_is_budget being campaign-level-only with the key ABSENT elsewhere, quality_score being keyword-only with nulls, and the approximate-share note when Google caps days.

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 long, but nearly every sentence earns its place by adding metric semantics, level-specific caveats, or routing guidance. It is front-loaded with the core purpose and return shape; however, the dense wall-of-text format with semicolon-heavy metric lists reduces scannability and could benefit from bullets or structured sections.

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?

There is no output schema and no annotations, yet the description covers the return structure, the metrics on summary and rows, per-level availability, id formats and downstream usage, and the Meta alternative. The only minor omission is explicit cursor/pagination semantics, but limit/cursor are already in the schema and the tool is otherwise fully specified for an agent to invoke correctly.

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 high (82%), but the description meaningfully exceeds the schema: it explains that ad_group/keyword levels share the cached sync with no extra API budget, that refresh spends Google API budget, the exact source of ad_account_id, the distinction between conversions and all_conversions, and the level-specific availability of quality_score and competitive metrics. This is far beyond what the schema provides.

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 precise verb-resource pair: "Get Google Ads performance insights for an account, at campaign, ad-group, or keyword level." It names concrete return components (account summary, previous-period comparison, sortable per-entity table, optional timeseries) and explicitly distinguishes the closest sibling by saying "For Meta insights use adsap_get_insights."

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?

It explicitly tells when to use the alternative (Meta insights via adsap_get_insights), explains the cache-first behavior and that refresh="Spends Google API budget", notes that ad_group/keyword levels "ride the same cached sync — no extra API budget," and tells where the ad_account_id comes from and how keyword ids should be passed onward. This is explicit when/when-not/alternative guidance.

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