Статистика

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

Beyond the readOnly/idempotent annotations, the description reveals important behavioral traits: the default aggregation level, the server-side limit of 100 detail rows, the tab-separated output without header for most report types, and the rejection of ALL_TIME without campaignIds for specific reports. This transparency helps the agent anticipate response format and potential errors.

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 but not overly verbose. It front-loads the primary purpose, then explains special cases and constraints. The structure is logical, though it could be slightly more concise by separating the general behavior from edge cases, but the current length is justifiable given the complexity.

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 14 optional parameters and the absence of an output schema, the description provides sufficient context: it explains defaults, output format differences, and key constraints. It does not explicitly define the exact structure of the returned report rows, but the indication of tab-separated values and the aggregated nature is enough for an agent to handle the response.

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?

While the schema covers 100% of parameters with descriptions, the tool description adds cross-parameter semantics such as the relationship between dateRangeType and dateFrom/dateTo, the effect of zeroClicksOnly/zeroConversionsOnly on detail rows, and the requirement to include Conversions in fieldNames for conversion metrics. This enriches the understanding beyond individual parameter definitions.

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 states the tool's purpose: it requests a performance report from Yandex Direct Reports service. It specifies the default report type and explains the returned data format, making the tool's function unambiguous and distinguishable from other statistics-related tools.

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 provides extensive usage guidance: how to get daily dynamics (add 'Date' to fieldNames), constraints on ALL_TIME for certain report types (must specify campaignIds or a limited period), and the special aggregated behavior of SEARCH_QUERY_PERFORMANCE_REPORT. This enables the agent to correctly configure parameters for different use cases.

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