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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds genuinely useful context: the [P0] priority marker and the important warning that the tool is temporarily disabled by WB. It also explains how to interpret coefficient values returned. However, it does not disclose response structure or whether results are filtered or paginated, so it is adequate but not rich.

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 [P0] marker and core resource statement come first, followed by the crucial coefficient semantics, then the disabled warning. Every sentence earns its place. The parenthetical Russian translation '(коэффициенты приёмки)' is mildly redundant but adds localization value without bloating the text.

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 tool with one optional filter and no output schema, the description covers the essential ground: the 14-day scope, the meaning of coefficient values (which effectively serves as the return-value contract), and the temporary disabled status. It is complete enough for an agent to invoke the tool correctly, though a stated return format would make it fully complete.

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 warehouse_ids already documented as 'warehouse filter,' so the schema handles the parameter documentation. The description adds no parameter-specific semantics beyond that, but its explanation of the coefficient value meanings indirectly helps an agent understand what the data represents after filtering. 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 identifies the resource as warehouse acceptance coefficients covering a 14-day window and goes further to explain the value semantics (0/1 with allowUnload=true means acceptance is open; x2-x7 multiplies cost). This makes the tool's purpose clear. It loses a point because it lacks an explicit verb like 'get' or 'list' and does not distinguish itself from related siblings such as wb_fbw_acceptance_options or wb_analytics_acceptance.

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 alternatives. The closing note 'Temporarily disabled by WB itself' is an availability warning, not usage guidance. Given there are related sibling tools (wb_fbw_acceptance_options, wb_analytics_acceptance), an agent receives no help choosing among them.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read-like operation by saying goods are 'available', but it does not explicitly state that it returns a list, how results are structured, whether pagination applies, or any side effects. For an unannotated tool, this is too thin.

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 a single compact sentence with no wasted words, and the core purpose is front-loaded. It is more of a fragment than a structured definition, but it is appropriately short for a simple one-parameter tool.

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?

With no annotations and no output schema, the description is the only source of context, yet it leaves the return format, parameter meaning, and relationship to sibling tools largely implicit. An agent might be able to guess what the tool does, but not confidently invoke it without additional assumptions.

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 says 'by subject IDs'. This essentially restates the parameter name and does not explain what subject IDs represent, how many can be passed, or what happens with invalid or empty values. It adds minimal semantic value beyond 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 states that the tool returns goods available for advertising campaigns, filtered by subject IDs. The resource (goods/nomenclatures for ads) and the scope (by subject IDs) are identifiable, and it is distinguishable from advert-listing or subject-listing tools. It loses a point because there is no explicit verb like 'get' or 'list', though the meaning is still clear.

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 alternatives such as wb_advert_subjects, wb_advert_list, or wb_advert_create. There are no conditions, prerequisites, or exclusions, so an agent must infer the intended usage from the name and context.

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?

With no annotations, the description carries the disclosure burden. It indicates the returned aspects (account, balance, bonuses) and implies a read-only lookup, but it does not explicitly state that it is a read operation or mention auth or response format constraints.

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 one short line and front-loads the resource and its fields. Minor redundancy ('balance' appears twice) and the parenthetical Russian translation add little but do not hurt.

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 read tool, the description names the main return components, which is adequate at a minimum level. However, with no output schema and no mention of currency/format or relationship to finance_balance, an agent still has some ambiguity about exactly what response to expect.

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 is empty, so the 0-parameter baseline of 4 applies. There are no parameter semantics to clarify.

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 the resource as the ad account and lists the data included (account, balance, bonuses), making the tool's purpose clear. It lacks an explicit verb such as 'retrieve' or 'get', and it does not differentiate from wb_finance_balance or wb_advert_budget, so it stops short of 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?

There is no guidance about when to select this tool over sibling alternatives such as wb_finance_balance, wb_advert_budget, or wb_advert_payments. Usage must be inferred entirely from the tool name.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. Saying 'recommended bids' implies a read operation but does not explicitly state whether the tool retrieves, calculates, or returns anything, nor does it mention side effects, auth requirements, or response behavior. This is nearly tautological with the tool name.

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 a single concise sentence with no filler or redundancy. The Russian parenthetical adds a helpful localization cue without bloating the text. Every word contributes to understanding the tool's purpose.

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 no output schema, no annotations, and zero schema description coverage, this description is too sparse. It does not explain what a caller should expect in the response, whether the operation is safe/read-only, or any constraints on the IDs. An agent could select the tool, but would lack important details for a fully informed invocation.

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. It adds some domain meaning by linking nm_id to 'card' and advert_id to 'campaign', which helps interpret the bare integer parameters. However, it does not explicitly map each parameter to its role, state expected formats, or explain how the two IDs interact.

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 resource and output: recommended bids for a card in a campaign. It distinguishes itself from the sibling wb_advert_bids_set by signaling a read/recommendation operation rather than a write operation. However, it lacks an explicit verb like 'get' or 'retrieve', so the action is implied rather than stated.

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?

No guidance is given about when to use this tool versus alternatives such as wb_advert_bids_set or wb_advert_cluster_bids. There is no mention of prerequisites, context, or exclusions. The usage context must be inferred entirely from the tool name and minimal description.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It communicates units and placement values but does not reveal whether the operation overwrites or merges existing bids, whether it applies immediately, what happens to unspecified bids, or what errors/effects may occur. This is a significant gap for a mutation endpoint.

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 extremely short and information-dense, front-loading the action and units. Every phrase contributes useful constraints, with no filler or repetition of schema details.

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 tool with full schema coverage, the description covers the input structure, units, and allowed placements. However, because there is no output schema and no annotations, the absence of behavioral details like whether this fully replaces existing bids leaves the tool only minimally viable for correct invocation.

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?

Although schema description coverage is 100%, the description adds non-obvious semantics: bids are in kopecks and placement is constrained to search/recommendations/combined. This goes beyond the bare schema structure and meaningfully clarifies how to construct the calls.

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 clear action ('Change CPM/CPC bids') on a specific resource ('bids'), and adds concrete units (KOPECKS) and placement values. It does not explicitly contrast itself with sibling tools like wb_advert_bids_recommendations, so it stops short of full sibling 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?

No guidance is given about when to use this tool versus alternatives, such as wb_advert_bids_recommendations for bid suggestions or other advert management tools. The placement enum hints at scope but does not state prerequisites, exclusions, or selection criteria.

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?

No annotations exist, so the description carries the full burden of behavioral disclosure, and it discloses nothing beyond a noun phrase. It does not state whether the operation is read-only or mutating (a real concern given mutation siblings like wb_advert_bids_set and wb_advert_pause), what it returns, or what happens on invalid input. This reads as a data-dictionary label, not a behavioral description.

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 short with no wasted words, but this is under-specification rather than genuine conciseness. The parenthetical Russian translation adds no information for an agent, and the single sentence could have conveyed the operation type and parameter meaning at the same length.

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 low-complexity (one integer parameter, no output schema, no annotations), which lowers the bar for completeness, yet the description still omits the operation type, semantics of 'budget' (spend limit vs. current spend), and return value. An agent cannot determine whether calling this tool has side effects or how to interpret the result. The description is inadequate even for a minimal one-parameter tool.

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 sole parameter advert_id has no inline documentation, so the description must compensate. 'One ad campaign' only implicitly ties the integer parameter to a campaign identifier; it never names advert_id, explains how to obtain a valid value, or clarifies that it is required. The compensation is minimal and indirect.

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 resource ('budget of one ad campaign') and narrows scope to a single campaign, which partially distinguishes it from list-level siblings like wb_advert_list. However, it is a noun phrase with no verb, so it never states whether the tool retrieves, sets, or updates the budget. It borders on tautology with the tool name wb_advert_budget and does not disambiguate from finance-related siblings like wb_advert_costs or wb_advert_balance.

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 the many similar advertising siblings, including wb_advert_balance, wb_advert_costs, wb_advert_stats, and wb_advert_payments. No context, conditions, recommended alternatives, or exclusions are provided, leaving the agent to guess which advertising finance tool fits its intent.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It correctly signals a write operation via 'Set' and clarifies the currency unit, but it does not say whether the provided bids replace or merge with existing cluster bids, whether the clusters must already exist, or what side effects (e.g., immediate campaign changes) the call has.

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 brief sentences with the core action front-loaded. The second sentence adds the valuable unit clarification, though the Russian parenthetical '(ставки на кластеры)' largely repeats the first sentence and adds little value for an agent.

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 mutation tool with an untyped array parameter, no annotations, and no output schema, the description is too thin. It omits how clusters are referenced or discovered, whether the bids array represents a full replacement or a partial update, and how this tool differs from wb_advert_bids_set. An agent would need to inspect other tools or guess to call it safely.

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% and the schema's inline example already defines the array item shape ([{advert_id, nm_id, norm_query, bid}]), so the baseline is 3. The description adds one genuinely useful detail — that the bid value is in RUB per 1000 views — but it does not clarify the semantics of norm_query, how cluster identifiers are obtained, or the valid ranges for bid values.

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 ('Set') and resource ('bids on specific search clusters') and adds the crucial pricing unit (RUB per 1000 views), so an agent knows what action is performed and on what. However, it does not explicitly distinguish itself from the closely related sibling wb_advert_bids_set, and 'specific search clusters' leaves the cluster identification model vague.

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 the very close alternatives in the sibling list, particularly wb_advert_bids_set (general bid setting) and wb_advert_clusters / wb_advert_clusters_stats (cluster retrieval). An agent cannot determine which bid-related tool to invoke for a given task, since no conditions or exclusions are stated.

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?

With no annotations, the description carries the full burden of behavioral disclosure. The verb 'Search' implies a read-only operation, but the description does not disclose output shape, whether it returns a list or a single cluster, pagination behavior, or any dependencies on campaign type or state. This is a significant gap for a tool with no structured safety metadata.

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 a single compact sentence that front-loads the core action and resource. The parenthetical adds useful domain context, though the 'P0' prefix is operational noise rather than functional description. Overall it is appropriately sized for a simple one-parameter tool.

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 no annotations, no output schema, and no parameter documentation, the description is too thin. It identifies the resource but leaves important operational details, such as what the returned clusters contain and how to interpret the response, completely unspecified. An agent would struggle to know exactly what to expect from the call.

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 schema has one required integer parameter, advert_id, with 0% schema description coverage. The description does not explain what advert_id represents beyond the vague phrase 'of a campaign,' leaving the agent to infer that it is the campaign identifier. The parameter name is self-explanatory, but the description compensates for the missing schema documentation only minimally.

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 ('Search') and a resource ('clusters of a campaign'), and the parenthetical clarifies these are search clusters/SEO queries. It is clear enough to identify the tool's purpose, though it does not explicitly distinguish it from related cluster tools like wb_advert_clusters_stats or wb_advert_cluster_bids.

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 alternatives such as wb_advert_clusters_stats or wb_advert_cluster_bids. The note that it replaced keyword phrases in 2026 offers some context about its domain, but it does not state conditions, exclusions, or preferred alternatives.

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?

With no annotations present, the description carries the full disclosure burden. It adds one genuinely useful behavioral trait beyond the schema — that daily=true produces per-day rows — and the phrase 'for a period' implies a date-range query. But it never states the operation is read-only, what the response contains, or how the nm_ids filter changes results, which for a stats tool are material expectations.

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 a tight two-clause sentence with the core action front-loaded before the parameter hint. The only questionable inclusion is the redundant Russian parenthetical 'статистика кластеров,' which restates the tool name without adding information for an agent.

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 no annotations, no output schema, and four of five parameters undocumented in the schema, the description leaves too much to inference: the shape of the returned stats, the date format, the semantics of advert_id, and the meaning of 'clusters' in the advertising context are all unspecified. It covers the basic idea but is not enough for an agent to call it correctly with confidence.

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 only 20% (just nm_ids: 'offer_id filter'), so the description must compensate, and it partially does: it explains daily's effect (per-day rows) and implies date_from/date_to define the period. However, advert_id — a required parameter — is left completely undefined in both schema and description, and the expected date string format is never mentioned.

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 ('Search cluster stats') on a defined resource ('cluster stats') within a defined scope ('for a period'), so an agent can tell this is a read operation over a time range. However, it never contrasts with the nearby siblings wb_advert_stats, wb_advert_clusters, or wb_advert_cluster_bids, so differentiation must be inferred from the name alone.

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 only usage direction is 'daily=true for per-day rows,' which is parameter-level guidance rather than tool-selection guidance. No alternatives are named, no when-to-use vs when-not-to-use conditions are given, and the agent gets no clue whether this or wb_advert_stats is the right choice for a given query.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not explain the return shape, granularity, currency, timezone, pagination, or whether this is a read-only historical view. The word 'history' implies a read operation, but that is not enough for a tool with no structured safety metadata.

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 a single, front-loaded sentence with no filler. It conveys the core purpose immediately, and the Russian parenthetical adds useful context for non-English users. No words are wasted.

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 that takes two required date parameters and returns historical data, the description omits important operational details like output format, date semantics, and relationship to sibling advert/finance tools. With no output schema and no annotations, the description alone does not give an agent enough to invoke it confidently.

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 only 50%: date_from has a format hint but date_to does not. The description adds only the vague phrase 'for a period,' which restates the two date parameters rather than clarifying date_to format, inclusive boundaries, or maximum range. It does not compensate for the missing schema documentation.

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 'Ad spend history for a period' clearly identifies the resource (ad spend/costs) and the scope (a date period). However, it does not explicitly distinguish itself from similar siblings like wb_advert_payments or wb_advert_stats, so it falls short of 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?

There is no guidance on when to use this tool versus related alternatives such as wb_advert_stats, wb_advert_payments, or wb_finance_report. The description only states what the tool returns, not the context or exclusions that would help an agent choose 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?

No annotations are provided, so the description carries the full burden of explaining behavior. It discloses that the tool provides counts by type and status but does not describe the return structure, whether it is read-only, or what 'get all campaign IDs' actually means behaviorally. This leaves important behavioral ambiguity.

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 extremely brief and front-loads the core purpose. The parenthetical Russian translation and the 'use to get all campaign IDs' clause add some redundancy and ambiguity, but the overall structure wastes little space.

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, the description is mostly adequate, but with no output schema it should clarify whether the result is a count, a list of IDs, or both. The ambiguous phrasing leaves an agent uncertain about the exact return value and how to consume it.

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 tool has zero parameters, so the baseline of 4 applies. There are no parameter details to clarify, and the description does not need to compensate for schema gaps here.

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 resource ('campaigns') and operation ('counts by type and status'), which distinguishes it from sibling tools like wb_advert_list or wb_advert_stats. However, the added phrase 'use to get all campaign IDs' muddles whether this tool returns counts or IDs, preventing a perfect score.

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 wb_advert_list or wb_advert_stats. The clause 'use to get all campaign IDs' provides an intended use case but does not state exclusions, prerequisites, or why an agent should prefer this tool over siblings.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses the campaign type and bid_type options, but does not mention side effects, prerequisites, whether creation auto-starts, billing implications, or what the response contains. For a mutating create operation, this is a significant transparency 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 short and front-loaded with the core purpose. However, the trailing Russian phrase '(создать кампанию)' is redundant and does not add information beyond 'Create ad campaign', so it does not fully earn 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?

With five parameters, no annotations, no output schema, and many related advert siblings, the description is incomplete. It explains neither expected return values, failure modes, prerequisites like balance or permissions, nor how this creation step interacts with other lifecycle tools.

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 high at 80%, so the schema already documents most parameters. The description adds a relationship between bid_type and placement_types, but this is largely restating the schema's own 'for manual: search, recommendations' note. Name remains undocumented in both schema and description, though it is required.

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 'Create ad campaign' and adds a specific campaign type ('type 9 Search+Catalog, the only one since 2026'), making the tool's purpose specific and distinct from sibling tools like wb_advert_list, wb_advert_start, or wb_advert_delete. The verb and resource are explicit and unambiguous.

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 use for creating a campaign and notes the campaign type is the only one since 2026, but it does not explicitly state when to use this tool versus alternatives or mention any exclusions. Usage context is only implied, with no direct guidance about sibling tools such as wb_advert_start or wb_advert_pause.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The explicit 'irreversible' marker clearly communicates that this is a destructive action with no undo, which is the most important behavioral trait for a delete operation.

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 one short sentence and front-loads the action and consequence. The parenthetical Russian phrase is redundant with the English text but harmless; it does not add semantic value.

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 destructive tool with no output schema, the description covers the essential information: what is deleted and that it is irreversible. It could be stronger by naming temporary alternatives, but nothing critical is missing for safe invocation.

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 sole parameter 'advert_id' is self-explanatory and the description maps it to the ad campaign being deleted. No additional detail is given about where the ID comes from or how it is validated, but for a single integer parameter this is minimally adequate.

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 ('Delete') with a clear resource ('an ad campaign') and adds the key qualifier 'irreversible'. This distinguishes the tool from siblings like wb_advert_pause, wb_advert_stop, wb_advert_start, and wb_advert_rename without any ambiguity.

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 the tool should only be used for permanent deletion, but it does not explicitly state when to use it versus alternatives such as pause or stop. The irreversibility warning provides context, but no exclusions or sibling references are given.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the mutation ('Top up') and source choices, but does not mention side effects, prerequisites, reversibility, authentication needs, or what happens after the deposit. For a fund-moving operation this is a notable 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 short and front-loaded with the core purpose. The source mapping is valuable, and the Russian parenthetical is mildly redundant but not harmful.

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 3-parameter mutation, the description gives enough to understand the operation and interpret the non-obvious 'source' parameter. Still, without annotations or an output schema, it would benefit from noting the expected result or any constraints around available funds.

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 only 33%, so the description must compensate. It adds meaning for 'source' with the 0/1/3 mapping, and 'campaign budget' implies advert_id identifies the campaign, but amount relies on the schema's 'amount, RUB' and advert_id is left implied.

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 ('Top up campaign budget') and a clear resource (campaign budget), which distinguishes it from read-oriented siblings like wb_advert_balance and wb_advert_budget. The inline source mapping adds additional precision about what the tool does.

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 verb 'Top up' implies the tool is for adding funds to a campaign, and the source options give some selection context. However, there is no explicit guidance about when to prefer this tool over related alternatives such as wb_advert_budget or wb_advert_payments.

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?

No annotations are provided, so the description carries the full burden of disclosing behavior. It only says 'Ad campaigns with settings and bids' and enumerates statuses; it does not state whether this is a read-only operation, how results are returned, whether pagination applies, or what limits exist beyond the schema.

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-loads the core resource. The status list is dense but directly relevant, and the Russian parenthetical adds localization context. There is little wasted text, though the missing action verb keeps it from being fully polished.

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 no output schema, so the description should clarify return shape and behavior; it mentions settings and bids and the schema covers all parameters, but pagination, response format, and the compact/full distinction are not described in the tool description itself. It is adequate for a simple optional-parameter list but not fully complete.

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 already documents ids, view, statuses, and payment_type, so the baseline is 3. The description adds the numeric status constants (9=active, 11=paused, 7=finished, 4=ready, 8=cancelled, -1=deleted), which are essential for correctly using the statuses filter and are absent from 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 names a concrete resource (ad campaigns) and the data it exposes (settings and bids), and the status list adds useful domain context. However, it lacks an explicit verb such as 'list' or 'retrieve' and relies on the tool name to convey the operation, so it does not fully distinguish itself from sibling advert 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?

There is no guidance about when to use this tool versus wb_advert_count, wb_advert_stats, or other advert tools. The statuses mapping implies filtering use cases, but the description does not state when to choose this tool or when to prefer an alternative.

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?

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose the read/write mode switch and the absence of plus-phrases, but it doesn't state whether setting replaces or merges existing phrases, what the read response looks like, or any permission/rate-limit considerations.

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, front-loaded with the resource and core operation. The note about no plus-phrases is concise domain context rather than padding.

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 no output schema and no annotations, the description covers the basic read/set modes but leaves the read response shape and the mutation semantics of norm_queries implicit. The optional nm_id parameter is essentially unexplained, so the description is adequate but not fully self-sufficient.

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 67%, and the description adds useful context by identifying 'Campaign' as the advert context and reinforcing norm_queries as the read/write switch. However, nm_id remains vaguely described as 'offer_id', and the exact semantics of norm_queries values are not elaborated beyond 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 opens with the specific resource, 'Campaign minus-phrases', and states both operations: read without norm_queries and set with them. This gives a clear verb + resource pairing and distinguishes the tool from the many other wb_advert_* siblings.

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 tells agents when to read (omit norm_queries) and when to set (include norm_queries). It doesn't name an alternative tool, but the note that WB has no plus-phrases since 2026 preempts a search for a plus-phrase counterpart.

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?

No annotations are present, so the description carries the full disclosure burden. It only labels the action as an emergency pause and gives an example; it does not state whether the action is reversible, idempotent, what state change occurs, or any side effects.

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?

One compact, front-loaded sentence with an urgency indicator [P0] and an illustrative case. No filler or redundant phrasing.

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 state-changing tool with no annotations and no output schema, the description leaves out expected behavior and how it differs from sibling wb_advert_stop and wb_advert_start. It is enough to understand the intent, but not enough to fully specify correct invocation and consequences.

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 description never mentions advert_id or explains how it maps to a campaign. With 0% schema description coverage, the description must compensate but does not; the parameter name is self-explanatory, but that is not tool-description value.

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 action ('Emergency pause') and a concrete resource ('ad campaign'), with a realistic trigger scenario. However, it does not explicitly contrast with sibling tools like wb_advert_stop, and the parenthetical Russian phrase 'остановить рекламу' uses 'stop' language that could blur the boundary.

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?

Provides a clear usage context: P0/emergency, with an explicit example threshold ('ДРР over 20%'). It does not mention alternatives or when not to use this tool, 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?

No annotations are provided, so the description carries the full burden of disclosing behavior. It implies a read-only query through the word 'history,' but it does not explicitly state that no mutation occurs, nor does it cover pagination, response contents, or required permissions.

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 a single front-loaded sentence with no fluff. The Russian parenthetical reinforces meaning without adding real clutter, and every part serves to explain the tool's purpose.

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 two-parameter history query, the description is minimally adequate: it names the domain, the date range, and the date format. However, with no output schema and no annotations, it falls short of explaining what the returned history contains or how the results are ordered/paged.

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 only 50%, with date_from described in the schema but date_to not described there. The description compensates by stating that both dates use YYYY-MM-DD, but it does not clarify inclusivity, date-range limits, or timezone behavior.

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 resource (ad account top-ups) and the operation (retrieving history for a date period). It is clear on its own, though it does not explicitly differentiate itself from related siblings like wb_advert_deposit or wb_advert_costs.

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 about when to use this tool versus similar advertising-finance tools. The phrase 'history for a period' implies a report-style lookup, but no alternatives or exclusions are mentioned.

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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only says 'Rename', implying a mutation, but does not mention side effects, permission requirements, idempotency, validation rules, or what response to expect. This is a significant gap for a mutation tool.

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 very short and front-loaded, with no filler or irrelevant detail. The Russian translation is redundant but not harmful. It is concise without sacrificing the core message.

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 two-parameter rename operation, the description provides a minimal viable understanding. However, there is no annotation coverage and no information about expected outcomes, error scenarios, or validation rules, so the contextual picture is incomplete for an agent that needs to invoke it reliably.

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 schema has 0% description coverage, so the description must compensate for the two parameters. It partially does: the description implies that 'advert_id' identifies the campaign and 'name' is the new name. However, it does not explicitly clarify which parameter is the target ID and which is the new value, or describe any name constraints.

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 ('Rename') and a specific resource ('an ad campaign'), making the tool's function immediately clear. It also distinguishes this tool from the many sibling wb_advert_* tools by naming the exact operation being performed.

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 about when to use this tool versus alternatives, nor any mention of prerequisites or exclusions. The description only states the action, leaving the agent to infer appropriate usage entirely from the tool name and description.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. Starting an ad campaign is a state-changing action with financial implications (budget spending begins), yet the description discloses no side effects, reversibility, or state requirements. It simply states the transition without its consequences.

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 a single efficient sentence with the core action front-loaded. The Russian parenthetical 'запустить рекламу' adds marginal value for non-English agents but is essentially redundant with the English text.

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?

Despite low structural complexity (one parameter, no output schema), the tool activates advertising spend and belongs to a state-transition lifecycle. The description omits prerequisites (is the campaign required to be paused or newly created?), side effects (spending begins), and return behavior — gaps that matter for a financially impactful action.

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 does not mention advert_id at all. The parameter name is self-explanatory enough that the gap is not severe, but the description adds zero meaning beyond 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 states a specific action ('Start') on a clear resource ('an ad campaign'), and the Russian gloss reinforces the meaning. It differentiates from lifecycle siblings like wb_advert_pause, wb_advert_stop, and wb_advert_delete via the distinct 'start' verb. However, it does not clarify whether 'start' is for newly created campaigns only or also resumes paused ones, leaving some ambiguity against wb_advert_create.

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 the many ad-lifecycle siblings such as wb_advert_create, wb_advert_pause, wb_advert_stop, or wb_advert_delete. No prerequisites (e.g., campaign must exist or be paused) or conditions for use are mentioned.

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?

There are no annotations, so the description carries the behavioral burden; it does disclose a rate limit, a maximum date range, and that results include a per-day breakdown. It does not explicitly state that the call is read-only, nor what happens when the rate/period limits are exceeded, which leaves some behavioral ambiguity.

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-loads the key output metrics before constraints and interpretation. The Russian parenthetical is mildly redundant, but the whole text is short and every major fact (metrics, daily breakdown, rate limit, period, profitability heuristic) is present without padding.

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?

With no output schema and no annotations, the description provides a useful but incomplete picture: it lists metrics, mentions daily breakdown, and sets limits, but does not clarify the response structure beyond 'days[]' or error behavior when constraints are violated. For a read-only stats endpoint with only three parameters, this is adequate but not thorough.

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 67%, with date_from and advert_ids documented but date_to not described. The description adds some meaning by specifying the 31-day period constraint and naming the metrics, but it does not define the exact formats or the shape of the returned daily breakdown, so parameter semantics are only partially enriched.

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 the tool as returning campaign statistics and enumerates the specific metrics (spend, views, clicks, CTR, CPC, orders, revenue) plus a daily breakdown, so an agent can tell it is a stats/reporting tool. It does not use an explicit verb like 'get' and does not name sibling tools, but the metric list makes the purpose unambiguous.

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 the tool should be used when campaign advertising metrics are needed, and it gives concrete constraints: a 3 req/min limit and a maximum period of 31 days. It does not state when to prefer this tool over similar siblings such as wb_advert_costs or wb_advert_clusters_stats, so alternative selection guidance is missing.

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?

There are no annotations, so the description must carry the behavioral burden. 'For good' communicates that this is a terminal, non-pause action, which is useful. However, it does not disclose side effects, reversibility, state requirements, or return behavior, so it only reaches a minimum viable level.

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 a single front-loaded sentence with no filler. It includes the key behavioral contrast ('unlike pause') and a helpful Russian gloss, making every part earn 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?

For a one-parameter action with no annotations and no output schema, the description conveys the core semantics of a permanent stop. It omits clarification versus wb_advert_delete and any state/undo details, leaving the definition adequate but incomplete.

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 never mentions advert_id or explains how to identify the campaign. The parameter is self-explanatory by name and type, but the description does not compensate for the missing schema-level documentation.

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 — 'Finish an ad campaign for good' — and explicitly contrasts it with pause, which helps distinguish it from wb_advert_pause. However, 'for good' leaves some ambiguity against wb_advert_delete, since an agent could interpret permanent finishing as deletion.

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 phrase 'unlike pause' gives clear contextual guidance: use this tool when the goal is to end a campaign permanently instead of temporarily pausing it. It does not fully spell out when-not conditions or contrast with other lifecycle tools like delete.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It communicates that the result is a set of advertising-related subjects, but it does not state whether the operation is read-only, what the response shape is, or whether any pagination or filtering behavior exists. It is not misleading, but it is quite sparse.

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 one short sentence with no filler and is front-loaded with the core meaning. The parenthetical Russian clarification adds useful context for the target domain without bloating the text.

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 no-parameter lookup tool, the description is nearly sufficient, but it leaves ambiguity against sibling tools and provides no usage or response context. It is minimally viable but not complete.

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 tool has zero parameters and the input schema is an empty object, so there are no parameter semantics for the description to clarify. Per the baseline for zero-parameter tools, this dimension is already satisfied.

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 resource ('subjects') and its purpose ('for ad campaigns'). The word 'available' implies a list/read operation, though no explicit verb like 'list' or 'get' is used. It is distinguishable from generic subject tools like wb_subjects_search because it scopes the subjects to ad campaigns.

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?

No guidance is provided on when to use this tool versus alternatives such as wb_subjects_search or wb_subject_charcs. The phrase 'for ad campaigns' gives a weak hint, but there is no explicit context, prerequisite, or exclusion to guide an agent's choice.

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 discloses 'Task-based, 10-60 s', which adds useful asynchronous behavior context beyond the schema. However, with no annotations, it does not explain what task-based means in practice, whether a polling step is needed, or how the final report is returned.

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 short sentences, front-loaded with purpose, and no filler. The task-based runtime hint and parenthetical clarification earn their place without bloating the description.

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 task-based report tool with no output schema and no annotations, the description is too thin. It does not explain how to retrieve the finished report, what the response contains, or the meaning of the two required date parameters, leaving an agent uncertain about the full invocation flow.

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 date_from or date_to at all. The parameter names are self-explanatory, but the description adds no value about expected date formats, ranges, or constraints.

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 paid acceptance report at WB warehouses, naming the resource and domain clearly. It lacks an explicit verb like 'generates' or 'retrieves', but combined with the tool name it is understandable. It is specific enough to generally distinguish from finance and warehouse sibling 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?

No guidance is given on when to use this tool versus alternatives such as wb_fbw_acceptance_options, wb_acceptance_coefficients, or other wb_analytics_* tools. The description does not state when this report is appropriate or when it should be avoided.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals only the weekly publication cadence. It does not explain whether the returned deductions are negative amounts, whether the data is cumulative, what authentication or scoping is required, or what happens for dates when no report was published.

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 a single front-loaded sentence with a parenthetical translation, making it compact and easy to scan. It wastes no words, though its brevity contributes to the lack of parameter and behavioral detail.

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 no annotations and no output schema, the description should at least clarify the date parameter semantics and the nature of the returned data. It only states topic and weekly publication, leaving an agent uncertain about exactly how to invoke the tool and what to expect.

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 schema documents only the date format (YYYY-MM-DD), and the description does not clarify what date should be supplied: the Wednesday publication date, the deduction occurrence date, or a request date. The 'published on Wednesdays' hint implies a constraint but does not explicitly define the parameter's meaning, leaving a critical ambiguity for a single-argument tool.

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 analytic resource: deductions for self-buyouts, and adds a distinguishing cadence ('published on Wednesdays'). This separates it from generic finance or deduction siblings like wb_deductions. However, it lacks an explicit verb such as 'returns' or 'lists', so the action remains implied rather than stated.

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 'published on Wednesdays' clause gives temporal usage context, suggesting this is a weekly-scheduled report rather than a real-time endpoint. It does not explicitly state when to use this tool over related finance or deduction tools, nor does it clarify behavior when the requested date is not a Wednesday.

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?

There are no annotations, so the description must carry the behavioral transparency burden. It does add useful behavior constraints: the date range is capped at 365 days and the call depends on parent and brand values from sibling tools. However, it does not clarify whether this is a read-only operation, what response shape to expect, or how invalid inputs are handled.

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 short and front-loads the core purpose and time constraint, followed by the key input dependency. The Russian parenthetical '(доля бренда)' is mildly redundant but not confusing. Overall this is efficient and 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?

With no output schema and no annotations, the description should cover return values and call expectations more fully. It explains where parent_id and brand come from and the date limit, but it does not describe what the tool returns, the format of date_to, or the exact sibling tool names. This leaves an agent under-informed for a four-parameter tool.

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 only 25%, with date_from having a format description and the other three parameters undocumented. The description partially compensates by identifying parent_id and brand as coming from sibling tools, but it uses 'parentId' instead of the schema's 'parent_id' and leaves date_to/date_from semantics mostly to inference beyond the 365-day cap. This is not enough for the low coverage level.

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 indicates the tool concerns 'brand share in a category' and adds the 365-day time limit. It also references the brand_share_parents/brands tools, which helps distinguish this report tool from the sibling tools that supply its inputs. A more explicit verb such as 'get' or 'calculate' would have made it 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 concrete usage guidance: the caller needs parentId and brand values obtained from the brand_share_parents/brands tools before invoking this tool. This establishes the prerequisite workflow clearly. It does not explicitly state when not to use this tool or name an alternative report tool, but the context is sufficient.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It conveys that the tool returns brands sold in the last 90 days and that the result is intended as input to brand-share, which is reasonable for a zero-parameter read-style listing. Still, it does not state output shape, uniqueness, pagination, or explicitly confirm a non-mutating read operation, so transparency is adequate but not thorough.

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 one compact sentence with no filler. It front-loads the core meaning ('Seller brands sold in the last 90 days') and then adds the purpose ('input for brand-share'), making every word useful.

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 no-parameter, no-output-schema tool, this is minimally sufficient: an agent can invoke it and understand the general return concept. However, it does not describe the returned brand identifier format or how the result relates structurally to the brand-share endpoint, leaving some ambiguity for downstream processing.

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 zero parameters and the schema description coverage is complete, so there are no parameter meanings to clarify. The baseline for a zero-parameter tool is 4, and the description does not need to compensate for any missing parameter documentation.

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 resource (seller brands) and a clear time window (last 90 days), and it explains the tool's role as input for brand-share calculations. However, it lacks an explicit verb like 'list' or 'get' and does not directly contrast itself with closely related siblings such as wb_analytics_brand_share or wb_brands_list, so it falls just short of full clarity.

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 phrase 'input for brand-share' implies the intended workflow: fetch the sold-brand list first, then feed it to brand-share analytics. There is no explicit 'when not to use' guidance or mention of alternatives among the many sibling analytics and brand tools, leaving usage context implied rather than stated.

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?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states what the tool conceptually returns and does not describe output format, date-range behavior, read-only nature, or any other operational traits beyond the minimal purpose.

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 a single concise sentence with no filler. It front-loads the core concept and adds context about being input for brand-share, though it is under-specified rather than richly concise.

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?

With four parameters, no annotations, and no output schema, the description is too thin to fully support correct invocation. It does not explain the meaning of the required date range, what the response will contain, or how the output should be fed into a brand-share call. The sibling context provides some orientation but does not fill these gaps.

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 only 25%, with just 'locale' briefly documented. The description adds slight clarity by indicating that 'brand' refers to the brand whose parent categories are returned, but it leaves date_from and date_to completely unexplained, and the locale values are only partially covered by 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 identifies a specific resource ('parent categories of a brand') and frames it as input for brand-share, which helps distinguish it from wb_analytics_brand_share and wb_analytics_brand_share_brands. However, it lacks an explicit verb such as 'get' or 'list', so it reads more like a noun phrase than a clear operation.

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 phrase 'input for brand-share' implies this tool should be used as a preparatory lookup before running brand-share analytics, and the sibling name wb_analytics_brand_share_parents reinforces that. There is no explicit statement of when to use it versus wb_analytics_brand_share_brands or wb_analytics_brand_share, nor any when-not-to-use 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?

With no annotations, the description carries the full burden. It does disclose a meaningful behavioral constraint (3 req/min) and indicates that results are compared to the previous period. However, it does not clarify response shape, aggregation behavior, authentication needs, or how the 'vs previous period' comparison is calculated.

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 a single dense sentence with the core metrics front-loaded and the rate limit appended. The Russian parenthetical 'воронка продаж' is slightly redundant with 'Sales funnel', but it does not meaningfully hurt clarity.

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 5-parameter analytics tool with no annotations and no output schema, this description is too thin. It does not explain what the return payload looks like, whether product filters are required, how date_to/date_from interact, or how this differs from adjacent analytics tools in the large sibling list.

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 only 60%, and the description adds little parameter-level meaning beyond 'per product', which loosely maps to nm_ids. Required date_to and the limit parameter remain undocumented in both schema and description, and the description does not compensate for those 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 states the resource ('sales funnel per product') and enumerates the delivered metrics: views, clicks, cart, orders, revenue, conversions, and previous-period comparison. It does not use a verb like 'get' or 'retrieve', and it does not explicitly distinguish itself from analytics siblings such as wb_analytics_history or wb_nm_report, but the per-product funnel framing gives reasonable purpose clarity.

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 the many analytics alternatives, no mention of required input conditions (e.g., must filter by nm_ids or brand_names), and no exclusions. The 'Limit 3 req/min' note is a rate-limit constraint, not usage 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?

With no annotations, the description must carry behavioral disclosure. It does disclose a meaningful rate limit, which is important. However, it does not describe the response format, pagination, whether the report is read-only, or any error conditions, leaving some behavioral gaps.

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 a single compact sentence that front-loads the core purpose and immediately follows with the critical rate-limit constraint. Every word earns its place, and the parenthetical clarification is useful for disambiguation.

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 relatively simple, with two date parameters and no output schema. The description names the domain and the rate limit, which is a solid start, but it omits what the report actually returns and any date-range semantics. It is minimally adequate but has clear completeness gaps.

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 only 50%: date_from has a YYYY-MM-DD format hint, but date_to has only a type. The description adds no parameter-level meaning and does not compensate for the undocumented date_to parameter. This is a clear gap.

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 the tool as a 'Chestny Znak excise/labeling report', which clearly conveys a reporting operation on a distinct domain (Russian excise/labeling data). It lacks a strong verb like 'get' or 'fetch', but the noun 'report' is sufficient and the domain separates it from the many sibling analytics 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 clear context: this is for Chestny Znak excise/labeling reports. It also gives a practical usage constraint with the 10-request-per-5-hours limit, which helps the agent plan calls. However, it does not explicitly name alternatives or state when not to use 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?

With no annotations, the description carries the behavioral burden. It discloses that the tool groups data, uses daily granularity, and compares periods, which is useful. However, it does not explain what the output looks like, how comparison is represented, or whether there are request constraints.

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 short and front-loaded, with the main scope in the first clause. The parenthetical Russian phrase repeats the English content and adds little value, but overall the description is efficiently sized.

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 there is no output schema, no annotations, and no parameter descriptions, the description is too sparse. It does not explain the return structure, how period comparison is configured, or what the optional aggregation_level can be set to, leaving important gaps for an agent.

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. It loosely maps 'by product groups' to nm_ids and 'per day' to aggregation_level, but it leaves date_from/date_to semantics, date formats, and aggregation_level values unexplained. The mapping is too vague to fully support correct invocation.

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 function: it returns a sales funnel grouped by product groups and day, and compares periods. This distinguishes it from siblings like wb_analytics_history and wb_analytics_detail, which do not explicitly signal product-group or period-comparison 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 implies when to use it—when sales-funnel data by product groups and daily period comparison is needed—but it does not explicitly state exclusions or name alternatives. An agent can infer the use case, but the guidance is not direct.

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?

With no annotations, the description carries the behavioral disclosure burden and does add meaningful behavior: data is aggregated by day and limited to the last week. It does not explain date semantics, response format, or error behavior, but the core behavior is visible.

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 a single compact sentence with the key qualifiers front-loaded: BY DAY, last week at most, conversion trends. There is no filler, and the Russian parenthetical adds clarification without redundancy.

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 no annotations, no output schema, and 0% parameter coverage, this description is too thin. An agent gets the core idea but not enough detail about parameter semantics, date format, response shape, or constraints beyond the week limit.

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 never names nm_ids, date_from, or date_to. The phrase 'last week at most' gives some indirect meaning to the date parameters, but nm_ids is left entirely to inference and no formats or constraints are provided.

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 analytical resource (sales funnel) with a clear aggregation granularity (BY DAY) and an explicit time limit (last week at most). It lacks an explicit verb and does not name sibling tools, but the core purpose is distinguishable from related analytics tools like wb_analytics_grouped_history.

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 a use case ('for conversion trends') and sets a clear time constraint ('last week at most'), which helps an agent understand when the tool is relevant. However, it does not explicitly mention alternatives or state when not to use 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?

With no annotations provided, the description carries the full disclosure burden and does add useful constraints: the 'Max 1000 nmID' limit and the 'Jam subscription' requirement are genuine behavioral traits. However, it fails to disclose the time window covered (the schema has no date parameter), which is significant for an analytics tool, and the cryptic 'Jam' reference is unexplained.

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 short fragments—and front-loads the core metrics list before constraints. The Russian parenthetical is mildly redundant for English readers and 'Jam subscription' is terse to the point of obscurity, but overall every sentence earns its place without padding.

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 minimal structured context (1 parameter, 0% schema coverage, no output schema, no annotations), the description is the sole information source and it covers the essentials: what it returns, the input limit, and a prerequisite. It remains incomplete because the reporting period is never addressed and the tool's relationship to the crowded analytics/stats sibling group is not clarified.

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, and it does add meaning: 'Max 1000 nmID' is a critical constraint on the array parameter and the Russian parenthetical 'рейтинг товаров, конверсия' clarifies the domain. Still, it doesn't explain what an nmID represents (product/article IDs), whether they must be the seller's own items, or value bounds, leaving the single parameter only partially documented.

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 clear resource ('Item rating') and enumerates the metrics returned (card views, cart adds, orders, conversions), so an agent knows what data to expect. The verb is implicit rather than explicit ('get'/'fetch'), and the tool is not explicitly differentiated from the many sibling analytics/stats tools, though the 'rating/conversion' focus is distinctive.

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 implied: 'Low conversion signals a card or price problem' hints at diagnosing product performance issues, and 'Jam subscription' hints at a prerequisite. However, the description never explicitly states when to choose this tool over siblings like wb_stats_sales, wb_stats_orders, or wb_nm_report, nor does it name any alternatives or 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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It adds useful context by stating the maximum date span and the required date format, but it does not describe the output shape, aggregation level, timezone behavior, or whether the operation is read-only. It is minimally transparent but leaves meaningful gaps.

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 extremely short and front-loaded, stating the resource and constraints in a single line. The Russian parenthetical '(продажи по регионам)' is redundant with the English text, which is a minor inefficiency, but overall there is almost no wasted space.

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 two-parameter analytics tool, the description covers the essential invocation details: what data is returned at a high level, the allowed date range, and the date format. However, with no output schema and no annotations, it leaves unspecified details like the exact fields in the response, grouping granularity, and relevant alternatives among the many analytics siblings.

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 parameter names date_from and date_to are self-explanatory, and the description adds important semantics by specifying the YYYY-MM-DD format and the ≤31-day span between them. It does not state inclusivity/exclusivity of the dates, but it compensates well for the empty schema 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 names the specific resource ('Sales by region') and adds key constraints (≤31 days, YYYY-MM-DD format), making the tool's basic purpose clear. It does not use an explicit verb like 'get' or 'list', and it does not contrast with sibling analytics tools, but the core intent is unambiguous.

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 this tool is for retrieving regional sales data and provides a clear date-range constraint and date format. However, it gives no explicit guidance on when to choose this tool over related siblings such as wb_stats_sales or wb_analytics_detail, and no exclusions or alternative routes are mentioned.

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?

No annotations are provided, so the description must carry the behavioral transparency burden. It only states the report's subject and categories; it does not disclose output format, pagination, performance characteristics, side effects, or any operational behavior. 'Interactive' is vague and not actionable for an agent.

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 a single compact sentence that front-loads the tool's core purpose and includes useful category vocabulary. The word 'interactive' adds little value, but overall there is no wasteful or repetitive text.

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?

With no annotations, no output schema, and only 25% parameter coverage, the description is far from complete. It does not explain the required date_from/date_to inputs, the meaning of limit or nm_ids, or what the returned report looks like. An agent would have to guess critical details before calling the tool.

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 only 25%, with date_from, date_to, and limit lacking descriptions. The tool description does not explain what these parameters mean, how dates should be formatted, how the limit applies, or what nm_ids filters. The description adds no parameter-level meaning and fails to compensate for the sparse 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 identifies a specific resource—stock and turnover reports—and adds the meaningful distinction of categorizing goods as healthy, scarce, and dead. It lacks an explicit verb but 'report' implies a read-style output. It does not explicitly contrast with sibling tools like wb_analytics_stocks_sizes or wb_stats_stocks, though its categories add some 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 gives no guidance on when to use this tool versus alternatives such as wb_stats_stocks or wb_analytics_stocks_sizes. There are no exclusions, no mention of required date context, and no indication of what distinguishes this report from similar analytics 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?

The description communicates a useful behavioral trait: the report is split by size and highlights non-liquid ('dead') sizes. The word 'report' also implies a read-only operation. However, with no annotations provided, the description carries the full burden and does not disclose how date filters, nm_ids, or limit affect behavior, or what the returned report contains.

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 a single focused sentence, front-loading the core purpose ('stock and turnover report split by size') before adding the dead-sizes finding. The Russian parenthetical adds clarity without significant bloat.

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 four optional parameters, no output schema, and no annotations, the description is too thin. An agent cannot tell whether nm_ids is required to get meaningful results, what date range is expected, how limit affects output, or what the report shape looks like. It is minimally selectable but not sufficiently invocable with confidence.

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 only 25%, with nm_ids described only as 'filter'. The description does not explain limit, date_from, or date_to, nor how they interact with the size-split report. Since schema coverage is low, the description was expected to compensate but provides no parameter-specific guidance.

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 (stock and turnover report), the grouping dimension (by size), and the intended analytical purpose (finds dead sizes / non-liquid leftovers). This distinguishes it from the closely named sibling wb_analytics_stocks, though it lacks an explicit verb like 'get' or '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 implies the tool should be used when size-level stock and turnover analysis is needed, especially for spotting dead sizes. However, it does not explicitly state when to prefer this over wb_analytics_stocks or other analytics siblings, nor does it mention any exclusions or prerequisites.

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?

No annotations are provided, so the description carries the burden of explaining behavior. It discloses the content type (seller news, API announcements) and the practical purpose (checking for breaking changes), which is useful. It does not mention output format, pagination, or whether the from_date filter is inclusive, but for a simple news-reading tool this is a reasonable level of disclosure.

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 a single sentence with no filler: it names the resource, states the relevant content, gives the practical use case, and even adds a Russian-language hint. Every element contributes value, and the key integration-risk purpose 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 tool with one optional parameter, full schema coverage, and no nested objects, the description is largely complete. It communicates what the news is about and why an integrator would call it. A minor gap is the lack of any hint about the response structure, but for a simple news listing this is not a blocking omission.

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 schema already describes from_date as 'news since YYYY-MM-DD' with 100% coverage, so the description adds no additional parameter meaning. Baseline 3 is appropriate because the schema handles parameter semantics fully, and the description does not need to compensate.

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 as WB seller news with a focus on API change announcements, and frames it as a way to check for integration-breaking changes. It is distinguishable from all listed sibling tools, none of which target news or API updates. It lacks a direct action verb like 'get' or 'list,' but the intent is unambiguous.

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 the tool should be used when checking for integration-breaking changes announced via WB seller news. It does not explicitly state when to use this tool versus alternatives, but no sibling tool serves a similar purpose, so the guidance is adequate. Absence of exclusions or alternative routing keeps it at a mid score.

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?

No annotations are provided, so the description carries the full burden of explaining behavior. It discloses that the tool concerns blocked or shadowed cards hidden from the catalogue, but it does not state whether the tool returns data, requires authentication, has pagination, or is read-only. The operation remains ambiguous.

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 a single compact sentence with no filler, and the core concept is front-loaded. However, it is a noun fragment without an explicit predicate, and the '[P0]' prefix adds operational priority rather than behavioral value for an agent.

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 tool with one optional boolean parameter, the schema plus description is enough to make a basic invocation. But there is no output schema and no description of the return format, and the lack of usage guidance leaves the definition only minimally complete.

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 already provides 100% coverage and clearly documents the only parameter: shadowed=true for shadowed, false for blocked. The description adds no meaningful detail beyond this, matching the baseline score for high 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 clearly identifies the resource: blocked or shadowed cards hidden from the catalogue, which distinguishes it from tools like wb_cards_list, wb_cards_trash, and wb_card_errors. However, it lacks a direct action verb such as 'list' or 'get', so the intended operation is implied rather than stated.

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 explicit guidance about when to use this tool versus sibling tools, nor any mention of alternatives or exclusions. The phrase 'lost sales' hints at a business context, but the description does not say under what circumstances an agent should invoke this tool instead of a related one.

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?

No annotations are provided, so the description carries the full burden of explaining behavior. It only says barcodes are generated but does not disclose whether barcodes are returned directly, saved to the system, what format they take, whether there are limits on the count parameter, or what side effects occur. This leaves significant behavioral ambiguity.

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 a single short sentence with no filler words, and the key verb and resource are front-loaded. It earns a slightly reduced score only because it is too sparse to convey much useful guidance.

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?

With one simple parameter and no output schema, the tool is relatively simple, but the description still omits essential context such as what the generated barcodes look like, how they are returned, and any constraints. The description is barely above the minimum needed to understand what operation is being performed.

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 explain the 'count' parameter at all. Although the schema default gives a small clue, the description fails to clarify what the count controls or how it affects barcode generation. The parameter semantics are effectively undocumented.

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 ('Generate barcodes') and a specific resource ('for new goods'), with the Russian term clarifying the domain. However, it does not differentiate from potentially related tools such as wb_supply_barcode or other barcode-related operations, so it is clear but not fully distinguished from siblings.

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 this tool should be used versus alternatives, no prerequisites, and no indication of what distinguishes 'new goods' barcodes from other barcode workflows. An agent would have to infer appropriate usage from the name 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?

No annotations exist, so the description carries the full burden of behavioral disclosure. It only states the resource and the filter effect; it omits output shape, pagination, optionality of subject_id, and any read-only or side-effect hints.

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 a single short sentence that front-loads the resource and the key filter. It is economical with no filler, though very terse.

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 one-optional-parameter list endpoint, the description is minimally viable: it says what is being listed and how filtering works. However, with no output schema and no annotations, it leaves gaps around response format, pagination, and the exact meaning of the category filter.

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 already describes subject_id as a category filter with 100% coverage. The description mostly restates this and adds only a Russian parenthetical, so it provides minimal additional meaning beyond 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 identifies the resource as seller brands and mentions the optional category filter, which is specific enough to understand the tool's purpose. It doesn't explicitly differentiate it from brand-related sibling tools, but the resource + filter combination is reasonably clear.

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 about when to use this tool versus alternatives such as wb_subjects_search or wb_analytics_brand_share_brands. No conditions, prerequisites, or exclusions 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal two traits: the response includes a replySign usable for answering, and chats may contain complaints or IP-holder claims. But it does not disclose whether this is a read-only fetch, whether it returns a list or a single chat, pagination behavior, or side effects. The replySign hint is useful but underdeveloped.

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 a single efficient sentence that front-loads the resource and the key answering hook before the content caveat. The Russian parenthetical 'чаты с покупателями' is redundant with the English name, which is minor waste, but overall the length is appropriate for a zero-parameter tool.

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 annotations and no output schema, the description should clarify the return shape and the replySign workflow. It does not state whether the tool returns a list of all buyer chats, how replySign should be consumed (e.g., passed to wb_chat_send), or how complaints/IP claims should influence handling. An agent has to guess the basic contract of the call.

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 tool has zero parameters and empty schema, so the baseline of 4 applies — there is nothing for the description to document. The replySign mention refers to output content, not an input parameter, so no parameter information is missing.

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 the resource (buyer chats) and a distinguishing feature ('includes replySign for answering'), which separates it from general chat tools like wb_chat_events. However, there is no explicit verb — the tool name is a plural noun implying list retrieval, but the description never states what operation it performs. It reads more like a content annotation than a functional definition.

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?

No guidance is given on when to use this tool versus closely related siblings such as wb_chat_send, wb_chat_events, or wb_chat_download. The description hints at the replySign being used 'for answering' but never states the relationship to wb_chat_send or when this tool should be selected over the alternatives.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the mutation ('Add') and target ('existing card'), without mentioning validation, idempotency, effects on existing nomenclatures, permissions, or error behavior. This is minimal for a mutation tool.

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 a single compact sentence that front-loads the action and target. The parenthetical 'добавить размер' adds relevant clarification without unnecessary length. Every part contributes to understanding the tool's purpose.

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 no annotations, no output schema, and an underspecified nested parameter object, the description is too sparse. To call the tool correctly, an agent would need the shape of cards_to_add items and clarity on success/failure behavior. The description provides only a high-level summary.

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 description adds meaning by explaining that imt_id refers to an existing card and cards_to_add contains the nomenclatures/sizes to add, which the schema mostly lacks. However, cards_to_add is an array of opaque objects with no structure defined, and the description does not specify required fields or formats. It partially compensates for the 50% schema coverage but not fully.

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 ('Add') and resource ('nomenclature/size to an existing card'), and identifies the targeting mechanism ('by imtID'). This clearly distinguishes the action from sibling tools like wb_cards_create or wb_cards_update. The Russian gloss 'добавить размер' reinforces the intended operation.

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 explicit guidance about when to use this tool versus alternatives such as wb_cards_update or wb_cards_create. The phrase 'existing card' implies a prerequisite, but no conditions, exclusions, or alternative tool routes are provided. An agent must infer usage solely from the action name.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only restates the purpose and does not mention the response format, the compact/full behavior, error cases, or the fact that this is a read-only operation.

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 a single short sentence with no filler. The parenthetical Russian gloss is slightly redundant but does not detract from conciseness.

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 2-parameter read tool with no output schema and no annotations, the description is too thin. It covers only the basic purpose and leaves the agent to infer return shape, view behavior, and how this tool differs from nearby card-related siblings.

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 both parameters are already documented structurally. The description adds minimal extra meaning by naming nmID as the key, but does not explain the view parameter's trade-offs beyond what the schema already says.

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 ('card') and the lookup key ('nmID'), which is enough to understand the operation as a details-retrieval call. However, it lacks an explicit verb such as 'get' or 'retrieve' and does not differentiate from sibling tools like wb_cards_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 gives no guidance on when to use this tool versus alternatives such as wb_cards_list, wb_card_errors, or wb_search_table_details. There are no stated exclusions, prerequisites, or selection criteria.

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?

No annotations are provided, so the description must carry the behavioral burden. It implies a read-only check operation but never explicitly states that it is non-mutating, what data it returns, or whether it may have side effects. The description names the error categories but leaves core behavioral expectations implicit.

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, front-loaded with the P0 priority, and every phrase adds value: severity, scope of errors, and intended frequency. There is no redundant or filler 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 zero-parameter tool, the description is reasonably complete: it names the resource and the error categories included. However, with no output schema and no explicit statement of return format, count, or fields, an agent still lacks some context about what the tool actually returns.

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 tool has zero parameters, so the description does not need to explain parameter meanings. It correctly focuses on what the tool reports rather than on input configuration.

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 a specific resource (cards with errors) and the action ('Check'), and specifies the scope: blocked/rejected cards including IP-holder complaints. This distinguishes it from related card tools like wb_cards_list and wb_card_detail by focusing specifically on error states.

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 a P0 item to check regularly. It does not explicitly contrast with alternative tools or state when not to use it, but the phrase 'Check regularly' provides concrete operational 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?

No annotations are provided, so the description carries the full behavioral burden. It conveys that this is a read-style operation on recommendations, but it does not disclose response structure, pagination, filtering behavior, required authorization, or any side effects. The brief noun phrase adds minimal behavioral context beyond the tool name.

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 extremely short, which is concise, but it under-specifies rather than being efficiently informative. It front-loads the core concept but leaves out essential usage and parameter context.

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 tool with no output schema and no annotations, the description should explain what nm_id represents, what kind of recommendations are returned, and how this relates to wb_card_recommendations_set. The current text is too sparse to fully support correct invocation and interpretation.

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 only required parameter, nm_id, is not explained at all. The description's phrase 'on a card' weakly implies nm_id identifies a card, but it never states the parameter's meaning, format, or acceptable values. The description fails to compensate for the missing schema documentation.

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 resource ('recommended goods on a card, cross-sell') and the verb is implied by the tool name 'get'. It clearly identifies what data the tool returns and is distinguishable from the sibling wb_card_recommendations_set, though it does not explicitly contrast them.

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?

No guidance is given on when to use this tool versus alternatives. It does not mention that wb_card_recommendations_set is for writing recommendations, nor does it describe prerequisites or typical call contexts. Usage context is only implied by the resource name.

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?

There are no annotations, so the description carries the full burden of disclosing behavior. It states that the operation is a set/mutation and includes the max-10 limit, but it does not explain whether the list replaces existing recommendations, what happens if more than 10 nmIDs are provided, or any validation/error behavior. For a mutating tool with no annotation support, this is a significant 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 a single concise sentence that communicates the core action, target, and a key limit. The Russian parenthetical adds minor contextual noise but does not significantly harm clarity or structure.

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 simple with only two required parameters, and the schema plus description are enough to infer the basic call shape. However, because there is no output schema and no annotations, the description leaves out important behavioral context such as overwrite semantics, error handling, and response expectations, making it only minimally complete.

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. It links 'card' to nm_id and 'recommended goods' to recommended_nm_ids, and adds the max-10 constraint. However, it does not explicitly define each parameter's role or mention constraints like whether duplicate or invalid nmIDs are allowed.

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 ('Set') and names the resource ('recommended goods on a card'), making the action and target unambiguous. Adding the 'max 10 nmID' constraint further pins down the tool's scope and differentiates it from siblings like wb_card_recommendations_get.

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 makes the usage context clear: this tool is for setting recommended goods on a card. It does not explicitly mention when not to use it or name alternatives, but the 'Set' framing and the obvious sibling wb_card_recommendations_get provide enough context for an agent to select it 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?

With no annotations present, the description must carry the behavioral disclosure burden itself. It usefully reveals that the operation is asynchronous and may take up to 30 minutes to sync, which is non-obvious and important. However, it does not disclose response behavior, failure modes, idempotency, or validation constraints, leaving notable gaps.

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 purpose and async behavior are front-loaded, the prerequisite is attached in a natural place, and the Russian parenthetical is a minimal translation aid rather than noise.

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 create operation with no output schema, the description covers the key operational facts: what it creates, that it is async, the sync delay, and the required upstream call. It stops short of explaining what the API returns or how to interpret success/failure, but the operation is simple enough that this is not a critical gap.

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 baseline is 3, but the description adds meaningful semantic value by telling the agent to fetch subject characteristics via wb_subject_charcs first, which directly informs the 'characteristics' field inside the cards payload. It also gives a compact realistic shape of the cards array structure, reinforcing 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 states the action ('Create new cards') and the resource (cards), immediately distinguishing it from card-management siblings like wb_cards_update, wb_cards_list, and wb_cards_move_to_trash. Mentioning the prerequisite wb_subject_charcs further clarifies what kind of cards this tool creates.

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 tells the agent to retrieve subject characteristics via wb_subject_charcs first, which is a clear and explicit prerequisite. It does not explicitly state when not to use this tool or name alternatives for creating vs updating cards, but the creation context plus prerequisite is strong enough 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only restates a noun phrase and does not reveal whether this tool is read-only, mutates state, requires authentication, or has side effects. This is a serious transparency 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 very brief and front-loaded, but the parenthetical Russian phrase largely duplicates the English phrase. It is under-specified rather than efficiently informative, lacking a clear verb or any operational detail.

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?

There is no output schema and no annotations, so the description should explain what the returned limits represent and what the agent should expect when invoking the tool. It does not, leaving the agent without enough context to know what the call will produce.

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 zero parameters, so there is nothing for the description to add about parameter meaning or usage. The baseline for zero-parameter tools is 4, and the description does not need to compensate for schema gaps since there are none.

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 the resource ('card create/edit limits') and suggests a domain, but it lacks a verb that tells the agent whether the tool retrieves, sets, or validates these limits. It does not meaningfully distinguish itself from sibling card tools such as wb_cards_create or wb_cards_update, so much is left to inference from the tool name.

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. With a large list of sibling card tools, the description provides no context about typical use cases, prerequisites, or exclusions, leaving the agent to guess when 'limits' is the relevant operation.

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?

No annotations are present, so the description carries the full behavioral disclosure burden. It only discloses cursor pagination; it does not state whether the list includes active or trash cards, what the response contains, or any size/rate implications.

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 a single front-loaded sentence with no filler; it states the action, includes a useful Russian translation, and adds the pagination hint. Every word 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?

There is no output schema and no annotations, and two object parameters are effectively opaque. The description does not explain the return shape, card status scope, or how to construct cursor/filter values, so it is not fully actionable.

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 schema already describes view, cursor, and filter (75% coverage), while the description adds little beyond restating cursor pagination. It does not clarify the filter object structure or limit semantics, but the schema carries most of the parameter meaning.

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 action and resource ('List product cards') with a clarifying Russian gloss, and identifies cursor pagination. It is clearly distinct from mutation and single-card tools, but it does not differentiate from related list endpoints such as wb_cards_trash.

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 word 'List' implies the use case of retrieving product cards, but the description provides no explicit when-to-use guidance, exclusions, or alternative tool routing. With such a large sibling set, it should ideally note that trash cards belong to wb_cards_trash and single-card lookup belongs to wb_card_detail.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It does reveal the 30-nmID limit and the merge/split conditional behavior, but it does not mention side effects, reversibility, permissions, or what happens to source cards after the operation.

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 a single sentence that front-loads the operation and packs the max limit and conditional behavior without filler. The Russian parenthetical is slightly redundant but does not add noise.

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 two-parameter mutation, the description is mostly usable, but with no output schema and no annotations it omits return behavior, error conditions, and consequences for the original cards. An agent can invoke the basic operation but cannot fully anticipate the outcome.

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 schema only documents target_imt, leaving nm_ids undescribed, and schema coverage is 50%. The description adds the 30-nmID cap and clarifies the target_imt conditional, but it does not fully explain the semantics of nm_ids beyond the tool name and merge/split context.

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 ('Merge/split cards') and a specific resource (cards), and adds the batch cap of 30 nmID plus the conditional target_imt behavior. This clearly distinguishes it from sibling tools like wb_cards_update or wb_cards_move_to_trash.

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 invocation logic: setting target_imt merges into that imtID, omitting it splits. This is clear context for when and how to use the tool, though it does not name alternatives or state explicit when-not-to-use conditions.

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?

No annotations are provided, so the description carries the full burden of disclosing behavior. It only restates the action ('Move cards to trash' / 'удалить карточки') without mentioning reversibility, side effects, required permissions, or result behavior. It does not contradict any annotation, but it leaves the behavioral profile thin.

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 a single action-first sentence with no unnecessary context. The Russian parenthetical '(удалить карточки)' is redundant with the English text, but the overall length is appropriate for a one-parameter tool.

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 one-parameter operation with full schema coverage, the description provides the essential action and input. However, with no annotations and no output schema, it omits the expected result and whether the action is reversible, leaving some ambiguity for an agent.

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 already documents nm_ids as 'nmIDs to delete' with 100% coverage. The description's 'by nmID' confirms the relevant identifier but adds no additional semantic detail 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 ('Move'), a clear resource ('cards'), a destination ('trash'), and an identifier type ('nmID'). It clearly distinguishes this from the sibling tool wb_cards_recover_from_trash, which performs the reverse operation.

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 alternatives such as wb_cards_trash for viewing trashed cards or wb_cards_recover_from_trash for restoring them. There is no stated context, prerequisites, or 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It communicates a state-changing action ('restore') but does not mention side effects, idempotency, whether already-restored or non-trashed nmIDs cause errors, permission requirements, or any other behavioral nuance an agent would need to anticipate.

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 one clear sentence with no filler, and the core information is front-loaded. The parenthetical Russian translation is redundant but harmless. It is appropriately concise for a simple one-parameter tool.

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 tool with one required parameter and no output schema, the description conveys the essential operation and relevant data needed to invoke it. It could be more complete by noting response behavior, but no critical invocation detail is missing for a straightforward restore action.

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% and the schema already describes nm_ids as 'nmIDs to restore', so the description adds little beyond confirming the parameter's role. This aligns with the baseline of 3 for a well-covered single parameter; the description does not introduce format, constraints, or edge-case details not already in 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 states a specific verb ('Restore'), a specific resource ('cards from trash'), and the key identifier ('nmID'). This clearly distinguishes the tool from siblings like wb_cards_move_to_trash and wb_cards_list, making the core purpose immediately obvious.

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 context 'from trash' implies the appropriate use case: restoring cards that were previously moved to trash. However, it does not explicitly mention when not to use it or name alternatives such as wb_cards_trash for listing trashed cards or wb_cards_move_to_trash for the reverse operation, leaving usage guidance largely 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?

With no annotations provided, the description carries the full burden of behavioral disclosure, but it only names a state ('in trash'). It does not say whether the operation is read-only, how pagination or limit behavior works, or what the response contains.

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 extremely short, but it is under-specified rather than genuinely concise. It is a fragment with no structured operational information and no front-loaded verb or purpose.

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 no output schema and no annotations, the description is far too incomplete. It fails to state the action, the result shape, or the behavior of the limit parameter, so an agent cannot confidently 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?

The schema has one parameter, limit, with 0% description coverage, and the description does not explain what limit means or how it affects results. The agent only gets the type and default value, not the parameter's semantics.

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 'Cards in trash (корзина)' is essentially a restatement of the tool name and lacks an explicit verb such as 'list' or 'get'. It identifies a resource category but does not clearly state what operation is performed, so an agent cannot tell whether this returns, counts, or otherwise manages trashed cards.

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 about when to use this tool instead of related siblings like wb_cards_list, wb_cards_move_to_trash, or wb_cards_recover_from_trash. No conditions, alternatives, or exclusions are mentioned.

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?

With no annotations, the description carries full responsibility for behavioral disclosure. It reveals only that the tool modifies cards, but does not state whether fields are overwritten or merged, whether card identifiers are required, any permission or validation concerns, or what the mutation produces in response.

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 a single, front-loaded sentence with no redundancy; the key verb and resource appear immediately and the optional Russian parenthetical adds minimal weight. Every part 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?

This is a mutation tool with no annotations, no output schema, and a single parameter whose schema description is tautological. The description gives a high-level field list but misses critical information for calling it correctly, such as how cards are identified, whether this is a bulk update, and what response is returned.

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 schema-only description is vague ('updated cards'), so the tool description adds real value by listing the actual updatable attributes (description, SEO, characteristics). However, it still omits the structural requirement for card identifiers or array element shape, preventing a 5.

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 clear verb ('Update'), a specific resource ('cards'), and enumerates the exact update targets: description, SEO, and characteristics. This distinguishes it from sibling card tools like create, list, detail, and trash operations.

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 wb_cards_create or wb_card_detail. The description only explains what the tool does, not when it should be selected or what prerequisites exist, leaving usage decisions entirely 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it discloses nothing — no read-only guarantee, no auth requirements, no pagination or return-format hints. It is behaviorally silent, though at least it does not mislead.

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?

At six words plus a parenthetical, the description is undeniably brief, but the Russian gloss duplicates the English 'parent categories' and earns no place. The brevity reflects under-specification rather than deliberate front-loading of an action.

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 simple (one optional parameter, no output schema, no annotations), but the description still omits the operation ('returns'), the return shape, and any differentiator from the many sibling catalog tools. An agent would have to infer the most basic facts about the call.

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% — the locale parameter is fully documented ('ru | en | zh, default ru') in the schema, so the baseline is 3. The description adds nothing about locale or any other parameter, which is acceptable because the schema already covers it.

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 resource ('parent product categories') with a Russian gloss, but it is a noun phrase with no verb — it never states that the tool returns or lists these categories. It does add domain context ('product') and scope ('All'), which distinguishes it from a pure restatement of the name, but the action must be inferred.

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 contains no when-to-use guidance, no exclusions, and no mention of alternatives. Given that sibling tools such as wb_directory, wb_subjects_search, and wb_brands_list occupy adjacent catalog territory, the absence of routing guidance leaves the agent guessing which tool to call.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It mentions that the tool changes status but does not disclose side effects, state transition rules, reversibility, permission requirements, or what happens when an invalid action is supplied.

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 short and front-loaded, with the action verb and allowed values placed prominently. The '[P0]' prefix and Russian gloss add minor noise but do not obscure the core information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.