Статистика

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds behavioral context: row-count semantics per grouping period, presence of a 'total' summary, metric group locations (base), and currency note for spent. However, it omits pagination behavior (offset/limit/autoPaginate) which remains only in schema, leaving a minor gap.

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 compact yet information-dense, with no filler. It front-loads the core purpose, then layers grouping, sorting, total, and metrics in logical sequence. Every sentence contributes actionable guidance, achieving high efficiency in three sentences.

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 tool's complexity (11 parameters, no output schema), the description covers the most critical pitfalls: grouping semantics, total field, server-side sorting, and metric locations. It does not explicitly mention that dateFrom/dateTo are required for day/week/month (though schema does), nor pagination mechanics. Still, for an agent to call correctly, the description provides sufficient orientation, meriting a 4 rather than 5.

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 100%, so parameters are already documented. The description adds semantic depth beyond schema: it explains the meaning of 'summary' vs period modes, gives a concrete sortBy example ('base.spent'), and clarifies that metrics groups like 'base' contain shows/clicks/spent. This extends the schema's basic field descriptions.

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 states a specific verb ('Возвращает статистику') and resource ('по кампаниям (ad_plans), группам объявлений (ad_groups) или объявлениям (banners)'), naming all three entity types. It clearly distinguishes this stats tool from sibling listing tools like list_ad_plans by focusing on statistical metrics rather than entity enumeration.

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 gives explicit when-to-use guidance for grouping modes: 'По умолчанию группировка summary — одна сводная строка на объект за весь период; day/week/month нужны ТОЛЬКО для динамики по дням и вопросов про тренд'. It also clarifies that the total field covers all objects so manual summation is unnecessary, and explains server-side ranking via sortBy/order.

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