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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add context – and it does: it discloses that the tool returns competitor medians plus concrete recommendations, and that it needs no token. It does not mention rate limits or how many competitor cards drive network load, but the added auth and return-shape context is genuinely useful.

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?

Front-loaded with the verb and resource, then a dense but purposeful metric list, closing with the return value and the no-token note. Every clause carries information; the long enumeration is the only reason it is not a 5.

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 two-parameter read-only tool with no output schema, the description covers what it does, what it compares, what it returns (medians + recommendations), and the auth requirement. Only the absence of guidance on competitor-count tradeoffs or return format keeps it from full marks.

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%: both 'article' and 'competitors' are documented in the schema, including the nmId format hint and the 3–10 recommendation. The description adds no format, bounds, or edge-case meaning beyond what the schema already states, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (audits a Wildberries product card) and enumerates exactly which dimensions are compared: photo, video, rich content, description length, characteristics, price, rating, reviews, negativity share, seller answers, delivery speed. This is far more concrete than a generic 'audit' tool, though it never names the closest siblings (wb_compare, wb_product_details) to draw the line explicitly.

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 one real usage signal is 'Работает без токена', which tells the agent no auth setup is needed. There is no explicit when-to-use vs wb_compare or wb_product, and no statement of when this audit is inappropriate (e.g. for a seller's own card already covered elsewhere). Usage is only implied by the comparison framing.

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

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety bar is covered; the description adds the auth-relevant fact "Работает без токена" plus the result-shaping behavior of flagging leaders per metric, which is not in any structured field. It still omits error behavior for invalid articles and any rate/limit context.

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 front-loaded sentence covers purpose, compared fields, and output; the short "Работает без токена" clause earns its place as auth context. The metric list is somewhat dense but not padded.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only comparison tool with no output schema, the description supplies the compared dimensions and the leader-marking result behavior, leaving nothing critical unstated for a correct 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?

Top-level coverage of the single parameter is 0%, and the description only implies plurality via "несколько товаров" — it never explains the nmId format, the 2-item minimum, or the 20-item cap. The format detail actually lives in the schema's items description, so the prose compensates for nothing.

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 precise verb ("Сравнивает") and resource ("несколько товаров Wildberries"), then enumerates exactly what is compared (цена, скидка, рейтинг, отзывы, остатки, срок доставки) and the output behavior (marks leaders per metric). This clearly separates it from single-product siblings like wb_product and wb_product_details.

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 parenthetical "например, свой и конкурентов" implies the competitive-analysis use case, which is useful context, but no sibling is named as an alternative and no exclusion is stated. An agent must infer that wb_product handles single lookups and wb_price_watch handles longitudinal tracking.

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

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuinely new behavioral context: it discloses the auth requirement (works without a token) and the nature of the output (weekly granularity, summary statistics), neither of which annotations convey.

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?

A single, tightly front-loaded sentence that names the resource, granularity, returned summary, and auth context with zero filler.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully previews the return values (min/max/current/change), which is what an agent most needs. It stops short of stating the covered time window or how to interpret the change field, but for a one-parameter read-only tool it is essentially 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?

Only one parameter (article), and schema coverage is 100%, with the schema itself explaining the nmId format and its origin in the catalog URL. The description adds no parameter-level detail beyond what the schema already provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: weekly price history for a Wildberries product, plus the summary fields it returns (min, max, current, change). The scope is clear and concrete. It does not, however, differentiate itself from the similar-sounding sibling wb_price_watch, so the agent must infer the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the read-only retrieval framing, and 'Работает без токена' hints at a context where credentials are unavailable. But there is no explicit when-to-use/when-not or reference to an alternative such as wb_price_watch vs this snapshot-history 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?

Annotations already cover the read-only/idempotent/open-world profile, so the bar is lower. The description adds genuinely useful context beyond them: 'Работает без токена' (auth requirement) and the set of output signals it produces (min/max/average, sharp drops/growth, sale flags).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action, then use case, then auth note. The flags enumeration is slightly list-heavy but each clause carries information; little waste.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A read-only tool whose annotations cover safety and which has no output schema; the description helpfully sketches the returned signals. What it does not cover is routing relative to sibling price tools, which is a minor gap given the clear capabilities stated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 50% schema coverage, the schema already documents 'weeks' and the article format. The description only indirectly touches parameters ('изменение за последние недели', 'нескольких товаров') without adding syntax or constraints beyond the schema, so it does not compensate for the coverage 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?

States a specific verb and resource ('Следит за ценами нескольких товаров Wildberries сразу') and enumerates what it returns (current vs history, min/max/average, changes, flags). The phrase 'нескольких товаров сразу' implicitly distinguishes it from the single-product wb_price_history, but no sibling is named explicitly.

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?

'Удобно регулярно проверять конкурентов и ловить, кто демпингует' gives a use context, but there is no explicit when-to-use/when-not guidance and no reference to alternatives like wb_price_history or wb_compare. Usage is only implied.

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

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description still adds real behavior beyond that: no token/auth required, support for one or many articles in a single call, and the filtering rule that out-of-sale products are omitted from the response – a non-obvious output behavior.

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 tight sentences, no filler. The returned-field list is front-loaded, followed by the two behavioral constraints (no token, out-of-stock excluded). Every clause carries information.

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, the description compensates by enumerating the returned fields and covering auth, batching, and missing-item behavior. Only minor gaps remain, e.g. error behavior for invalid or unknown articles and any rate limits.

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 single parameter is fully documented there (nmId format, valid positive integer, source link, max 50). The description only restates 'по артикулу' and adds no format, batching, or range detail beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (WB product by nmId) and enumerates exactly what is returned – price, discount, rating, review count, seller, stocks, delivery time. It does not, however, distinguish itself from the sibling wb_product_details, so an agent cannot tell the two apart from the description 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?

Usage is only implied: listing the returned fields suggests when the tool is useful, and 'Работает без токена' signals it is usable in a no-auth context. There is no explicit when-not or naming of alternatives such as wb_product_details or wb_price_history, despite many overlapping 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description's 'Только чтение' is redundant with those annotations, though 'works without a token' adds genuine auth context. It does not describe response shape or limits, so it adds only modest value beyond structured fields.

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?

Dense but well-organized: returned fields are front-loaded, then usage, then sibling routing and safety note. Every clause earns its place, though the safety clause is partly redundant with annotations.

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, the description usefully enumerates the returned card fields, which is exactly what an agent needs to judge relevance. It stops short of describing nesting/format of characteristics, but is largely complete for a single-param read tool whose annotations carry the safety profile.

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 single 'article' parameter is well documented in the schema (nmId, derived from the catalog URL). The description adds no parameter syntax beyond the schema, so the baseline of 3 applies; the mention of 'артикул продавца' refers to a returned card field, not the input, and is not confusing in 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?

States a specific resource (the textual content of a Wildberries product card) and enumerates exactly what it returns: name, item/category, seller article, full description, characteristics and composition. It also explicitly demarcates itself from siblings by naming where price/rating/stock and reviews live.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit use case ('study how the seller describes the product, or compare descriptions') and routes the agent to alternatives with conditions: wb_product for price/rating/stock and wb_reviews for reviews. Nothing is left to inference.

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

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

Annotations already cover readOnly, idempotent, openWorld and non-destructive. The description adds genuinely new behavioral context beyond them: 'Работает без токена' (no authentication needed) and the default negativity threshold of 1–3★. It doesn't mention rate limits or result volume, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the core action and scope, followed by outputs and use case. Every sentence carries information; a slightly tighter phrasing could still improve it.

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, the description usefully enumerates what is returned (repeated phrases/words, share of negatives, share of answered reviews, fresh examples). Combined with the no-token note and the argument format, an agent has enough to invoke it correctly, though limits (10 articles per call, result size) are left to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%, and the schema itself already documents both articles and the max_stars threshold. The description adds only the default range (1–3★) for the negativity cutoff, which partially reinforces but does not extend parameter semantics; 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 gives a specific verb and resource (собирает негативные отзывы) plus the multi-product scope and the analytics performed. It is clear what the tool produces, though the distinction from sibling wb_reviews (single-product) is only 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?

It states the practical context ('найти слабые места конкурентов или своего товара и идеи для улучшения'), which gives the agent a clear scenario for use. It does not name alternative tools or say when not to use it, so it stops short of the top band.

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

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

Annotations already declare readOnly, idempotent, open-world, non-destructive. The description adds genuine extra context beyond them: 'works without a token', meaning no authentication is required. It does not disclose pagination or how the rating distribution 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 sentences, front-loaded with the resource and its returned content, then the use case and the auth note. No filler; every clause 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?

With 100% parameter coverage and no output schema, the description usefully enumerates what each review contains (text, pros, cons, seller reply) and the token-free access, which compensates for the missing return schema. Only pagination/response-shape detail is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so article, limit and max_stars are fully documented in the schema itself. The description describes the content of returned reviews but adds no syntax or format detail beyond the schema — baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (rating distribution and latest customer reviews for a WB product) with the fields returned (text, pros, cons, seller reply). Clear enough to distinguish it from the seller-side sibling tools, but it never explicitly differentiates from wb_review_insights.

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?

'Useful to understand what a product or competitor is praised or criticized for' gives a clear use case, so usage is implied rather than asserted. It names no alternative tool and no when-not-to-use condition, leaving routing against wb_review_insights and wb_seller_feedbacks to inference.

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

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

Annotations already mark this as non-read-only and non-idempotent. The description adds valuable behavioral context: the reply is published publicly, user consent is required before invocation, and a specific WB_API_TOKEN scope ('Отзывы и вопросы', not read-only) is needed. This goes beyond the structured fields without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three short sentences, each earning its place: purpose, consent requirement, and auth prerequisite. It is front-loaded with the core action and contains 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 simple two-parameter mutation tool, the description covers the essential operational context: what it does, the public visibility consequence, required consent, and token scope. It does not describe return values or error cases, but no output schema exists and those details are not necessary 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?

Schema description coverage is 100%, so the schema already fully documents both parameters ('id' from wb_seller_feedbacks and 'text' of the reply). The description does not add significant extra meaning about parameter formats, constraints, or relationships beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Публикует ответ продавца на отзыв покупателя') with a clear resource and consequence: the reply will be publicly visible on WB. This differentiates it from sibling wb_seller_answer_question, which targets questions rather than feedback.

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 should be used to publish a seller's reply to a customer review, and it explicitly instructs the agent to show the text to the user and get consent before calling. It does not explicitly mention alternatives or when not to use it, so it stops short of a 5.

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

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

Annotations already indicate a non-read-only, non-idempotent write operation. The description adds meaningful behavioral context: the answer becomes publicly visible on WB, user consent is required, and a non-read-only token is needed. There is no contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short, purposeful sentences: the operation comes first, then the consent requirement, then the authorization prerequisite. There is no filler, no repetition of schema fields, and the important constraints are 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 two-parameter mutating tool, the description covers the purpose, public visibility of the outcome, the consent prerequisite, and the required auth scope. It does not describe the response or confirmation behavior, but with no output schema and a simple publish action, that is a minor 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?

The schema documents 'id' well ('id вопроса из wb_seller_questions'), but 'text' has no semantic description beyond min/max length. The description mentions showing 'текст' to the user, indirectly identifying it as the answer content, but it does not explicitly map both parameters or add format guidance. At 50% schema coverage, the description only partially compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb 'Публикует' and a specific resource: a seller's answer to a buyer's question. It also notes the answer is visible to all on WB, and the mention of 'вопрос покупателя' distinguishes this from the sibling wb_seller_answer_feedback.

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 a clear precondition: show the text to the user and obtain consent before calling. It also states the required token scope ('Отзывы и вопросы', not read-only). It does not explicitly name alternatives or exclusion cases, but the usage context is reasonably clear.

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

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive). The description adds value beyond them by disclosing the authentication requirement and its exact scope (WB_API_TOKEN with 'Reviews and questions') plus the default result filtering, which an agent cannot infer from 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?

Two short sentences with zero waste, front-loading the resource and scope first, then the credential requirement. Nothing redundant.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with no output schema the description is adequate on identity and auth, but it omits pagination semantics (skip/take) and any hint about result shape or limits (take max 5000), which matter 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?

Schema coverage is only 33% — only 'answered' is documented in the schema. The description supplements this by restating the default (unanswered) and explaining that returned ids are for replying, but 'skip' and 'take' (pagination) remain unexplained in both places, so compensation is partial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: customer reviews on the seller's products, with a default filter (unanswered) and the fact that each item carries an id for replying. This clearly separates it from a generic review tool, though it never names a sibling explicitly (e.g. wb_reviews) to sharpen 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?

Usage is only implied — the default 'unanswered' behaviour and the 'id for reply' hint at the workflow with wb_seller_answer_feedback, but there is no explicit when-to-use or when-not-to-use guidance versus siblings like wb_reviews.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the token-validation framing, which is useful behavioral context, but does not disclose anything about the returned payload beyond name/ID since no output schema exists.

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 what is returned and then the practical use. Nothing is redundant or padded.

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 trivial zero-parameter, read-only identity lookup with no output schema, stating what is returned (name and ID) and the token-check use case is sufficient. Additional detail on response shape would be minor.

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 takes zero parameters, so there are no parameter semantics to document; the baseline for a no-param tool applies. The description correctly implies no input is required beyond the configured token.

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 clearly what the tool returns (seller name and ID) tied to the token, which is a specific resource. It implies it is the seller-identity lookup, distinguishing it from siblings like wb_seller_orders or wb_seller_sales, though it doesn't call out an alternative by 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?

Explicitly gives a use case — verify that the WB_API_TOKEN works — which tells an agent when this tool is appropriate. It stops short of naming when-not-to-use or pointing at a sibling alternative, but the context is concrete.

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

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

Annotations already declare it read-only, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: the required token scope («Статистика») and the WB rate limit of one request per minute, both of which affect call behavior.

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 tight sentences: the first front-loads what the tool returns, the second carries the prerequisites. No filler. Could be marginally better only by adding the sibling contrast, which is not a conciseness issue.

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, the description compensates by enumerating the returned metrics, and it covers auth scope and rate limits. For a simple two-optional-date read tool this is largely complete; only the absence of sibling routing guidance is a minor 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% — both date_from and date_to, their format pattern, and the default (7 days back) are already documented in the schema. The description only gestures at 'за период' and adds no syntax or default detail beyond what the schema provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Заказы продавца за период') and enumerates the returned metrics (count, sum, cancellations, daily breakdown, top SKUs), which meaningfully distinguishes it from siblings like wb_seller_sales. However, it never explicitly names which sibling to prefer over this one, so differentiation is implicit 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 'за период' framing and the WB_API_TOKEN («Статистика») prerequisite imply the usage context, and the 1-req/min limit tells the agent when it can call. But there is no explicit when-to-use guidance or contrast against alternatives such as wb_seller_sales, leaving the agent to infer the 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds useful context: the token category required, and the fact that prices are shown without SPP or WB promotions (i.e., seller-set prices only), which is a non-obvious behavioral constraint. However, it does not mention pagination defaults, rate limits, or response structure, leaving some behavioral aspects to the schema. With annotations carrying the safety profile, a 3 reflects moderate added value beyond structured fields.

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 compact sentences: the first specifies the core purpose and fields, the second distinguishes from siblings, and a final sentence gives the token requirement. It is front-loaded with the essential purpose and contains no filler; every sentence earns its place.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with no output schema, the description provides the required token category, clarifies the pricing scope (without SPP and WB promotions), and points to appropriate alternatives. It is almost complete; the only minor gap is lack of pagination guidance, which is not strictly necessary since limit and offset are self-explanatory in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents limit and offset with defaults and ranges. The description adds no additional parameter details (e.g., maximum limits or pagination behavior). Baseline 3 is appropriate when the schema fully covers parameters.

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 verb+resource: it returns the current prices of the seller's own goods in the seller's cabinet, and lists exactly which fields are returned (WB article, seller article, price before discount, seller discount %, price after discount). It explicitly distinguishes itself from siblings wb_product and wb_price_watch by noting that those show the storefront price and competitor prices, which this tool does not.

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 states exactly when to use this tool (for the seller's own set prices without SPP and WB promotions) and names two alternatives for different use cases: wb_product and wb_price_watch for storefront and competitor prices. It also gives the authentication prerequisite (WB_API_TOKEN with category 'Цены и скидки').

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

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

Annotations already declare readOnly/idempotent/non-destructive, and the description restates 'Только чтение' (largely redundant), but it adds genuinely new behavioral context: result ordering (newest first) and the required WB_API_TOKEN scope «Отзывы и вопросы». No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded with the return contents first, then defaults, then routing, then auth. Every sentence carries information; only the 'Только чтение' clause is redundant against the annotations.

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, the description compensates by enumerating the returned fields, and it adds ordering, default filtering, mandatory token scope, and the follow-up tool. Nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so skip/take/answered are already documented, and the description mostly repeats the answered default rather than adding syntax or format detail. A useful bonus is noting that the returned id feeds wb_seller_answer_question, but this is baseline-level for a fully documented 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?

States a specific verb+resource (list of buyer questions about the seller's products) and enumerates the returned fields (id, date, text, SKU, product name, answer). It also distinguishes itself from the sibling wb_seller_answer_question, which is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the operative default ('По умолчанию — только вопросы без ответа') and routes the agent onward: pass the id to wb_seller_answer_question to reply. Clear context for when to use it, though it does not state explicit exclusions or when not to use it.

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

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

Annotations already mark this read-only, idempotent and non-destructive, and the description adds genuinely new operational context: the exact token scope required (WB_API_TOKEN with «Статистика») and the WB rate limit of 1 request per minute. These are precisely the auth and throttling facts an agent cannot get from annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tightly packed sentences: what is returned first, then auth requirement, then rate limit. No filler and the highest-value constraint (token scope) is not buried.

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, the description carries the burden of describing results, and it does name the metrics returned. It stops short of explaining aggregation shape, whether returns are broken out separately, or result size limits, which would matter for an agent parsing the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both date parameters (including their ISO pattern and default windows) are fully documented by the schema. The description only refers generically to «за период» and adds no format or boundary semantics beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (sales and returns for a period) and enumerates the payload: quantity, buyer payments, seller payout, top SKUs by revenue. This is clearly distinguishable from siblings like wb_seller_orders, wb_seller_stocks or wb_seller_prices without opening any schema.

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 period-based reporting and its preconditions (Statistics-scope token), but never states when to choose this over wb_seller_orders or other analytics siblings, nor any when-not condition. Usage is inferable from the resource name 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely new operational context beyond them: the required WB_API_TOKEN with the 'Statistics' category and a ~30-minute data refresh cadence. It does not state pagination or response size limits.

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?

Front-loaded with the resource, then the return contents, then use case, then auth and freshness caveats. Semicolon-separated clauses are dense but each carries information; nothing is padding, though it could be tightened slightly.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only listing tool with no output schema, the description adequately conveys what is returned, the auth requirement, and data freshness. Missing only minor operational details like pagination or result caps, which keeps it from a 5.

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 single parameter already carries a full description, so the schema does the heavy lifting; baseline 3 applies. The description only restates that low_threshold is the cutoff for the 'running out' lists, adding little beyond what the schema 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 names a specific resource (own goods' stock at WB FBO warehouses) and enumerates exactly what it returns per SKU: totals, per-warehouse breakdown, in-transit both directions, plus out-of-stock and running-out lists. This clearly separates it from siblings like wb_seller_orders, wb_seller_sales, and wb_seller_prices.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete use case: 'use this to understand what it's time to supply.' That is clear context for when to reach for the tool, but it stops short of naming alternatives or exclusions (e.g., how it differs from wb_seller_sales for demand analysis).

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