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.

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

Annotations only declare readOnlyHint=true, so the description carries the burden of behavioral disclosure. It reveals that Href appears only for text ads and is empty for graphic, video, and smart ads, with the count shown in ads_without_href. It also explains defaults for include_archived and limit range, transcending the annotation.

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 well-structured with a summary line, usage rationale, parameter list, and response caveat. It is somewhat repetitive about Href being present only here, but the repetition occurs in different contexts (differentiation and response behavior) and reinforces a critical point.

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 an output schema exists and readOnlyHint is present, the description is remarkably complete. It covers purpose, when to use, parameter semantics, and a subtle data caveat (empty Href for non-text ads). An agent has enough context to invoke the tool correctly and interpret results appropriately.

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 description coverage is 0%, and the description compensates by explaining the filter parameters (campaign_ids, ad_group_ids, ad_ids) as narrowing the selection with empty meaning all client ads. It also clarifies include_archived defaults and limit's 1–1000 range. client_login is not explained but is a self-evident required identifier.

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 clear statement of the tool's content: ads and landing pages — where ads lead, what's in headlines, whether UTM links are marked. It explicitly distinguishes itself from other report types by stating that the Href field exists only here and nowhere else, so an agent can differentiate it from siblings like direct_report.

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 provides explicit when-to-use guidance: call it when analysis reaches questions about which page a group goes to, whether it's one main page for the account, and whether there are labels — and before any conversion conclusions. It also warns about the misleading similarity of expensive clicks on irrelevant pages, which gives a concrete reason for preferring this tool.

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

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

The readOnlyHint annotation already covers safety. The description adds a little context about the returned data shape (id, name, type, status) and the mapping purpose, but doesn't explain behavior like archived inclusion, pagination, or response size. This is adequate but not rich, so a 3 is appropriate.

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?

Two terse sentences: the first states the payload fields, the second states the purpose. Every word is useful and front-loaded, with no filler.

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 simple read-only list with an output schema and two fairly self-explanatory parameters, the description covers the resource, the fields, and the purpose. The main gaps are that include_archived's effect on deciding 'which campaigns to pull' is left to inference and sibling differentiation is absent, but an agent still has enough context to invoke it 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 description coverage is 0%, and the description contains no parameter-specific guidance. 'Кампании клиента' only implies the client_login parameter, while include_archived is not addressed at all, so the description does not compensate for the schema gaps.

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 resource ('client campaigns') and enumerates the useful fields (id, name, type, status), and states the mapping purpose. It lacks an explicit verb like 'lists/retrieves' and doesn't explicitly differentiate from sibling tools such as direct_ads or direct_report, so it is not a 5.

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 a concrete use case: mapping CampaignId → campaign name and deciding which campaigns are worth including in a report. This is clear context for when to call the tool, but it doesn't mention when not to use it or name an alternative, so it stops short of a 5.

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

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

Annotations declare readOnlyHint=true, and the description adds useful behavioral context by specifying the authentication/header expectation: it is called without a Client-Login header because it is an agency method. This goes beyond the annotation and helps the agent invoke it correctly in the broader tool workflow.

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 and front-loaded: the first sentence states the purpose, the second explains how it fits into the workflow and how it should be called. Every sentence earns its place with no filler.

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 simplicity, one optional parameter, the readOnlyHint annotation, and the presence of an output schema, the description covers everything an agent needs: what the tool returns, where it fits in the workflow, and the required call context.

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 description coverage is 0%, and the description does not mention the limit parameter at all. The schema provides a name, type, and default, so the parameter is not opaque, but the description fails to add any meaning or guidance beyond that.

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 action (list) and resource (agency client logins), and adds scope by mentioning currency and balance. It also distinguishes itself from sibling tools by explaining that this is where client_login is obtained for other tools, and that it is an agency-level method.

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 clear usage context: it is the source of client_login for other tools and must be called without the Client-Login header, identifying it as an agency method. It does not name specific alternatives or explicitly say when not to use it, but the positioning is clear enough for an agent to route correctly.

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

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

Annotations already mark the tool as readOnlyHint=true; the description adds the key behavioral facts that no API request is made and no credits are consumed. This goes beyond the annotation and helps agents select the tool for cost-free local reads, though it does not cover edge-case behaviors like invalid paths.

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 two short sentences with no filler. The core action, object, and distinguishing benefit are front-loaded, making it easy for an agent to parse quickly.

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 simple three-parameter shape, an output schema, and readOnly annotation, the description covers the essential workflow: reading an existing report from a direct_report path without extra cost. Minor gaps such as explicit prerequisites and pagination parameter details are not severe.

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 description coverage is 0%, so the description must compensate, but it only explains the source of 'path' and vaguely suggests pagination via 'page by page'. The limit and offset parameters are not explicitly tied to pagination semantics, maximum values, or behavior when omitted beyond schema defaults.

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 uses a specific verb ('Постранично прочитать' — read page by page) and a specific resource ('уже выгруженный отчёт по пути из direct_report'). It clearly distinguishes this tool from sibling direct_report by stating it reads an already exported report without re-calling the API.

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 clear context: use this tool after a report has been exported via direct_report, when you want to read it without another API call or credit cost. It does not explicitly state exclusions or compare with alternatives beyond direct_report, but the intended workflow is clear.

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

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

Even with readOnlyHint=true, the description adds substantial behavioral detail: Direct does not check region codes so invalid codes cause silent wrong-region data, matches include a path to root because names are non-unique, invalid ids are returned as unknown_ids, the full directory is not returned, and the reference is loaded once per process so repeated calls do not consume points. This goes far beyond the annotation and fully informs the agent of expected edge cases.

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 well organized: a short purpose plus a critical warning up front, then per-parameter explanations in a consistent format, and a final constraint note. Every sentence adds operational value, and the structure makes it easy to scan.

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?

The description is complete for an agent to invoke the tool correctly: it covers when to call, why it matters, all parameters and their constraints, expected special return behavior (unknown_ids, path), and a prerequisite about agency tokens. Since an output schema exists, return values beyond what is described do not need to be spelled out.

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 description coverage is 0%, but the description compensates by thoroughly explaining each parameter: query with examples and case/ё-insensitivity, ids with the unknown_ids output, client_login with a clear condition and source, and limit with a 1–200 range. It also clarifies the logical constraint that at least one of query/ids is required, which the schema does not convey.

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 clear statement of what the tool does: returns Direct region codes by name and reverses-validates existing codes. It is unambiguous and distinct from all sibling tools, which are about clients, campaigns, wordstat, ads, and reports, none of which provide region reference lookups.

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 explicitly states when to use this tool: 'Вызывать всегда, когда в geo_ids (direct_wordstat) или RegionIds (direct_campaign_setup) уходит регион'. It also explains why this is critical (Direct does not validate codes and silently returns wrong-region data), gives the requirement that at least one of query/ids is needed, and clarifies that client_login is only required for agency tokens and can be taken from direct_list_clients.

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

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

Annotations only say readOnlyHint=true; the description goes further by disclosing that the tool writes a TSV to disk, returns path/totals/first rows, only has data for the last 3 years, and that multiple attribution_models produce per-model rows. It also explains field classes and the limit/order_by interaction. No contradiction with readOnlyHint.

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 each sentence adds information needed to call the tool correctly; the main behavior is front-loaded and parameter details are organized. There is no filler or repeated schema content.

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 11 parameters and no schema-level descriptions, this covers all parameters, the side effect, output shape, and key API behaviors; the output schema fills in the remaining return-type details. No critical calling information 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?

With 0% schema description coverage, the description must carry the documentation burden, and it does: every parameter is explained with formats, examples, allowed values, and constraints. It even gives the filter/order_by JSON structure and warns which field classes are not output columns.

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 uses a specific verb ('Выгрузить статистику') and names the resource (Reports API), then distinguishes the tool by its side effect: it writes a TSV to disk and returns the path, totals, and first rows. This is enough to distinguish it from siblings like direct_read_report.

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 context and constraints, such as data availability for 3 years, required client_login, and that conversions require goals, but it never explicitly states when to use this tool instead of direct_read_report or direct_campaigns. Usage must be inferred from the output-on-disk behavior, so guidance is implied rather than explicit.

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

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

The description goes well beyond the readOnlyHint annotation: it mentions writing a full list to disk, returning only a summary, that client_login is unnecessary, that Shows is monthly search demand rather than a campaign forecast, that invalid geo codes fail silently, and that the method is unavailable in sandbox. This is rich behavioral disclosure with no contradiction.

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 every sentence adds value, especially because the schema provides no parameter descriptions. It is well organized: behavior first, then use cases, then parameter details, then caveats. Nothing is redundant or filler.

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 a 4-parameter schema and no schema descriptions, this description covers purpose, use cases, all parameters, caveats, and environment limitations. An output schema exists, so the lighter treatment of return structure is acceptable. Nothing important 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?

Schema description coverage is 0%, and the description compensates fully: phrases explains the 50-phrase limit and Yandex operators, geo_ids gives examples and default behavior, min_shows and top are both explained with meaning and bounds. Every parameter receives practical context that the schema lacks.

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 names the exact resource (Yandex Wordstat) and the specific output: monthly search frequency, co-occurring queries, and similar queries, plus a summary per phrase. This clearly distinguishes it from siblings like direct_report or direct_regions, even without explicit sibling comparisons.

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 second paragraph gives explicit use cases: semantic collection, diagnosing low impressions, and separating demand decline from campaign decline. It does not name alternative tools or state when not to use it, so it stops short of a 5.

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