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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds genuinely useful behavior beyond annotations: it makes no API call to Metrika and requires no token, preventing the agent from assuming the token/auth obligations that sibling data tools carry.

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?

Three sentences, each earning its place: what it lists, when to invoke it, and the behavioral caveat about no API/token. The core function is front-loaded.

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 zero-parameter tool with no output schema, the description covers purpose, invocation triggers, and behavior. It also describes the return content (declared tools, hidden tools, enablement instructions), which substitutes for the missing output schema.

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?

Zero parameters, so the schema covers 100% and the baseline of 4 applies. The description confirms the tool is callable without arguments and states what the empty call yields.

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: it lists Yandex Metrika tools with their current visibility status, profile-hidden tools, and enablement instructions. It is clearly distinguished from all 10 siblings (stat_*, counter_*, goal_*, segment_* data tools) because it is a meta-tool about the server's own catalog, not a data-access tool.

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?

Gives explicit trigger conditions: call when the needed Metrika tool is not visible in the list or when the user asks what the server can do. It doesn't name specific sibling alternatives, and the when-not is only implicit (use it for discovery, not data operations), so it stops short of a full 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 already declare readOnlyHint, idempotentHint, and non-destructiveHint, so the main safety profile is covered elsewhere. The description adds the concrete GET endpoint and a documentation link, but no additional behavioral traits such as authentication, rate limits, or response structure.

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 text is short and includes the endpoint URL and documentation link, which are useful. However, the opening clause 'Информация о счетчике' is redundant with the second sentence 'Возвращает информацию об указанном счетчике'.

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 get-with-id tool, the schema, annotations, endpoint URL, and documentation link are mostly sufficient for an agent to call it correctly. The lack of an output schema and vague 'returns information' wording leave room for improvement, but the definition does not omit critical invocation requirements.

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 100%: counterId, field, and callback all have descriptions in the input schema. The tool description itself adds no parameter-level meaning beyond the schema, so the baseline of 3 is appropriate.

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 ('Возвращает') and identifies a concrete resource ('информацию об указанном счетчике'), so an agent knows it is a get-by-id operation for a single counter. It does not explicitly contrast with sibling metrika_counter_list or the statistics tools, but the phrase 'указанном счетчике' signals the narrowed scope.

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 implies that this tool is for retrieving details of a specific counter, and the required counterId parameter reinforces that context. However, it does not name sibling alternatives or state when to use metrika_counter_list instead, so usage guidance is only implicit.

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 declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the description does not need to establish that this is a safe read operation. It adds the concrete GET endpoint and a documentation link, plus the 'available to the user' scoping, which is context beyond annotations, but it does not describe pagination behavior or response shape.

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 brief and includes useful endpoint and documentation links, but the opening phrase 'Список доступных счетчиков' redundantly repeats the title before the next sentence restates it. It is efficient overall, but not every phrase earns its place.

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 schema documents the parameters thoroughly and annotations signal a safe read-only operation, so the description is adequate for a simple list call. However, there is no output schema inherited, and the description does not explain the response envelope, pagination, or metadata beyond saying it returns a list of counters.

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 100%, so all 14 parameters are already documented in the input schema. The description adds no additional parameter-level meaning, so the baseline score of 3 applies.

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 action ('Возвращает список существующих счетчиков') and scopes it to counters available to the user. It is easy to distinguish from the sibling metrika_counter_get by the 'list' semantics, though the description does not explicitly call out that distinction.

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?

There is no guidance on when to use this tool versus alternatives such as metrika_counter_get or the metrika_stat_* reporting tools. The intended use is only implied by the word 'list', and no exclusions or alternative routing are provided.

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 provide readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds context about being a GET request and provides documentation link, but does not disclose behavior beyond that, such as pagination limits, response structure, or error conditions. With annotations covering safety, 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?

The description is concise, with three sentences. It front-loads the purpose, then provides the API endpoint and a documentation link. The documentation link could be considered additional but is useful for deeper context. No wasted words.

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 that this is a read-only list operation with a simple schema (3 parameters, 1 required) and annotations cover safety, the description is adequately complete. It does not explain return values, but without an output schema, agents may wonder about the response format. However, the documentation link compensates slightly. It is not overly complex.

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 100%, so each parameter is already described in the schema. The description does not add extra meaning beyond what the schema provides, but it does mention the resource (goals) that the counterId refers to. The description does not elaborate on the callback parameter's usage or the useDeleted flag beyond schema defaults, but schema is sufficient.

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 that it returns information about goals of a counterched in a clear verb and resource. However, it does not distinguish from sibling tools like metrika_segment_list or metrika_counter_get, which could be confused for similar list operations. The inclusion of the API endpoint adds specificity but less differentiation.

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 implies usage when you need to list goals for a specific counter, but it does not explicitly state when to use it over alternatives. It does not mention prerequisites like the counterId being valid or user permissions. No explicit exclusions or when-not-to-use guidance is provided.

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 declare readOnlyHint, idempotentHint, and non-destructiveHint, so the description's main added value is the API-created scope and the GET endpoint. It does not contradict the annotations, but it also does not add details like pagination, response shape, or authorization requirements.

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 definition is short, readable, and front-loaded with the main purpose. The first sentence is somewhat redundant with the title, but the second sentence plus the endpoint and documentation links provide useful, compact context with minimal waste.

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 one-parameter, read-only, idempotent GET operation with rich annotations, the description is sufficiently complete: it names the resource, the counter scope, and the endpoint. The lack of output schema details is mitigated by the tool's low complexity.

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?

The input schema has 100% description coverage: counterId is documented as 'Идентификатор счетчика.' The description references the counter but adds no additional meaning beyond the schema, which is acceptable at the baseline for complete schema coverage.

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 список', and identifies the exact resource: API-created segments belonging to a given counter. This clearly distinguishes it from sibling tools such as metrika_goal_list or metrika_counter_list.

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 clearly conveys when to use the tool: when you need API-created segments for a specific counter. The qualifier 'созданных с помощью API' acts as an implicit exclusion of manually created segments, though the description does not explicitly name alternative tools.

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 cover readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the GET endpoint and the time-series behavior, but it does not describe response format, pagination, authentication needs, or limitations. It is consistent with the annotations and adds modest behavioral context beyond them.

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 but somewhat redundant: the first sentence restates the title, and the second partially repeats it before adding the useful example breakdown. The endpoint URL and documentation link are valuable, though a merged, front-loaded sentence would 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?

For a complex 22-parameter API with no output schema, the description gives the core purpose, endpoint, and documentation link, but does not describe what the returned data looks like or how the time grouping maps to API output. It is adequate for tool selection but not fully self-contained for a correct call without referring to docs.

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 100%, so the parameters are already well documented. The description adds conceptual context for the grouping behavior ('by days, weeks, months'), which relates to the group parameter, but it does not systematically explain parameters beyond what the schema already offers.

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 resource (Yandex Metrika statistics) and the key behavior: retrieving data with a time breakdown (by days, weeks, months). It identifies the query type for charts and dynamics tracking, though it does not explicitly differentiate itself from sibling tools like metrika_stat_data.

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 says to use this query type for building charts and tracking dynamics, which gives a clear when-to-use context. It does not mention when not to use it or name alternative tools, so it stops short of full routing guidance.

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 establish the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar for the description is lower. It adds the HTTP GET endpoint and states the response arrives as a table. It does not go deeper — nothing about pagination, sampling behavior, or limits — but nothing contradicts the annotations.

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 — four sentences conveying the core concept, endpoint, and documentation link. The first sentence slightly restates the title, but the content is otherwise front-loaded and free of 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 read-only tool with 23 fully documented parameters and no output schema, the description gives the essential conceptual model (A/B segments, per-segment dates and filters, table output) plus an endpoint and a full documentation link. It could add return-value or pagination details since no output schema exists, but the annotations and 100% schema coverage keep this adequate.

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 100%, so each of the 23 parameters is already documented and the baseline is 3. The description adds a mild semantic layer by explaining the A/B pairing, which helps the agent understand date1_a/date1_b/date2_a/date2_b and filters/filters_a/filters_b as per-segment groups. It lists no parameter syntax or examples beyond what the schema provides.

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 a specific operation — comparing two data segments (сегмент А и сегмент B) — with a clear verb, resource, and the ability to set distinct date ranges and filters per segment. This distinguishes it from sibling stat tools like metrika_stat_data or metrika_stat_pivot. However, it doesn't explicitly call out the closest sibling, metrika_stat_comparison_drilldown, leaving some differentiation to inference.

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?

Usage context is only implied: the tool is for comparing two segments with different date ranges and filters, which the description states. There is no explicit when-to-use vs. alternatives guidance, no exclusions, and no mention of when metrika_stat_data or metrika_stat_comparison_drilldown would be more appropriate. The docs link is provided, but the description itself leaves routing decisions to the agent.

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 declare readOnly/idempotent/non-destructive hints. The description adds behavioral context: for each grouping value the API returns two sets of metrics, and per-segment date ranges and filters can be set. This goes beyond annotations and helps the agent understand the response shape and configurability.

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 reasonably compact, starting with the core purpose and then elaborating with a concrete example of return structure. It includes the endpoint URL and documentation link but is not overly verbose. The structure is clear and front-loaded.

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 has 27 parameters and no output schema, the description is insufficient. It omits crucial details about how the drilldown mechanism works (e.g., parent_id, tree traversal), pagination, error handling, and how the two metric sets are structured in the response. The documentation link is not accessible to the agent, so the description alone does not provide enough guidance for correct usage.

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 all 27 parameters have description in the input schema. The tool description adds minimal parameter-specific insight, only mentioning per-segment filters and dates in general terms. It does not compensate beyond the schema, so the baseline of 3 applies.

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 this method combines Drill down and Comparison segment methods, and explicitly explains it returns two sets of metrics per grouping for comparing segments. It names the endpoint and distinguishes itself from the sibling tools by describing the combination behavior.

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 says 'using this method you can combine Drill down and Comparison' which gives clear context for when to use it relative to the separate tools. However, it does not explicitly state when NOT to use it or mention alternatives, so it lacks explicit exclusions.

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 declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is clear. The description adds the specific HTTP GET endpoint and a documentation link, which are useful behavioral details. However, it does not describe pagination, sampling behavior, or error conditions, but these are not essential given the rich schema and annotations.

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 relatively short, but it contains redundancy: 'Таблица.' repeats the titlecars, and 'Возвращает результат в виде таблицы' restates the previous point. The useful endpoint and documentation links are included. It is not overly long, but not every sentence earns its place.

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 too generic for a tool with 10 siblings. It does not explain what makes this endpoint distinct (e.g., plain data without drilldown/pivot/comparison aggregations) or when a caller would prefer it. The missing output schema is not a major issue, but the lack of sibling differentiation leaves the description incomplete for correct selection.

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 100%, with all 19 parameters documented in the input schema. The description itself does not mention any parameters, so it adds no semantics beyond the schema. Baseline 3 is appropriate.

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 that the tool provides access to Yandex Metrika statistical data, including report data, and returns a table. However, this is extremely broad and does not distinguish it from siblings like metrika_stat_drilldown or metrika_stat_pivot, which also provide statistical data. The title 'Таблица' adds little specificity, and the phrase 'returns the result as a table' is true of all stat 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 gives no guidance on when to use this tool versus its siblings. It does not mention alternatives, exclusions, or typical use cases. An agent would not be able to decide between metrika_stat_data and the other stat_* tools based on this text alone.

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 annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no behavioral details beyond the functional purpose (e.g., pagination, tree navigation, or response format). It does not contradict annotations, but adds minimal value in terms of behavioral disclosures.

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 concise and front-loaded with the core purpose. The opening 'Drill down.' is somewhat redundant with the title, but the subsequent sentence adds meaningful detail, and the API endpoint plus documentation link are useful. No unnecessary fluff.

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 tool is complex (21 parameters, no output schema), and the description provides minimal context for an agent to understand the drilldown concept or navigate the hierarchical response. While the schema is thorough, the description does not compensate for missing output schema or explain how tree levels relate to parameters like parent_id or include_undefined.

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 100%, so the schema already documents all 21 parameters. The description includes no parameter-level information, so it adds no value beyond the baseline 3.

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 that the tool generates a multi-level (tree-like) report with each level corresponding to one grouping. This is a specific verb+resource (drill down, build hierarchical report) and distinguishes it from flat-report siblings like metrika_stat_data, though it does not explicitly name alternatives.

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 no guidance on when to use this tool versus its siblings. It does not mention alternatives, conditions, or exclusions. The use case is only implied by the purpose statement ('drill down'), leaving selection to inference.

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 declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds the time-breakdown behavior and an endpoint URL, but does not disclose auth needs, rate limits, sampling effects, or response format. This is adequate but not rich beyond annotations.

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?

Three short sentences lead with the purpose, then the use case and links. No filler or repetition, though the documentation and endpoint could arguably be combined. Efficient and front-loaded.

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 tool has 22 parameters, no output schema, and only a minimal description. The description does not explain the response structure of a pivot report (rows vs columns, pivot_dimensions role, pagination via limit/offset), which an agent would need to interpret results correctly. Given the tool's complexity, the description is too thin for full call success.

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 100%, so parameters are already fully documented. The description adds no parameter-specific semantics beyond the generic 'time breakdown' context, which is not tied to any parameter. Baseline 3 applies.

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 identifies a specific verb+resource ('Получение сводной таблицы') and clarifies the capability as data with time breakdown for charts and dynamics. It is clearer than a tautology, but it does not explicitly contrast itself with siblings like metrika_stat_data or metrika_stat_bytime, so an agent may still need to infer the exact scope.

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 an intended use ('для построения графиков и отслеживания динамики'), which is a clear context signal. However, it provides no exclusions and names no alternatives among the many stat siblings, so guidance on when not to use this tool is absent.

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