direct_account_settings

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

Beyond the readOnlyHint annotation, the description discloses meaningful behavioral details: sections are independent and errors arrive per-section in an 'error' field while other sections still return, empty campaign_ids triggers server-side selection of up to 50 non-archived campaigns with a truncated signal, and bid adjustments multiply with each other. This is exactly the kind of non-obvious behavior an agent needs.

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?

Every sentence adds information: purpose, usage context, parameter semantics, and behavioral caveats. The structure is front-loaded with the core purpose, then parameters, then edge-case behavior, with no filler or repetition of schema-visible facts.

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?

For a tool with three parameters and an output schema, the description covers all essential operational information: what sections exist, what empty campaign_ids means, the 50-campaign limitation, truncation signaling, partial error behavior, and the multiplicative semantics of adjustments. The output schema can handle return-value details, so nothing needed for correct invocation is missing.

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?

Despite 0% schema description coverage, the description fully compensates: it enumerates the valid section values (bid_modifiers, retargeting_lists, negative_keyword_sets), explains the empty/default behavior for sections, and describes the server-side default behavior and 50-campaign cap for campaign_ids. The required client_login needs no further explanation due to the schema.

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 reading account settings absent from reports: bid adjustments, retargeting conditions, and negative keyword sets. It explicitly contrasts with Reports API data ('Reports API покажет статистику... но не покажет выставленный коэффициент'), distinguishing it from the sibling reporting 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?

It gives explicit when-to-use guidance: 'Нужен при разборе «почему кампания не работает» и перед выводами по срезам отчёта.' It also explains why Reports API alone is insufficient and that this tool supplies the missing diagnostic context, making the choice between this tool and reporting siblings clear.

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