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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context: inclusive date range semantics, today's incompleteness, attribution settings, empty-result dict shape, breakdown options, daily series behavior, conversions vs. actions caveat, and the ~2000-row cap with warning object.

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 content is front-loaded and every major point earns its place, but the description is very dense and has some repetitive date-range explanations. It is appropriately sized for the tool's complexity, though formatting could be tighter.

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 complex date logic, breakdown options, error handling, and conversions caveat, the description is complete enough for correct invocation. Return values are largely covered by the output schema, but the description still explains key response shapes and edge cases.

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?

With 0% schema description coverage, the description fully documents all 8 parameters: days, daily, since/until formats and precedence, date_preset enumerated values and error, breakdown allowed values, campaign_id scope, and workspace slug.

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: adset performance metrics (impressions, clicks, spend, conversions) for the last N days, sorted by spend. It also distinguishes scope from meta_campaign_performance by noting totals_only=True for account sums, though it does not explicitly contrast with meta_ad_performance.

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 explains when to use daily=True for Google Ads comparisons, precedence between since/until, date_preset, and days, and the effect of campaign_id filtering. It names the alternative for account totals and documents the foreign_object error condition.

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