ProfilDoors: межкомнатные двери в Москве

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real value beyond that by enumerating the returned fields and disclosing the non-obvious pricing rule ('цена «от» у дверей за полотно'), which an agent would otherwise misinterpret.

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

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

Three short sentences, front-loaded with the purpose, then the return contract, then the one caveat that matters. No filler and nothing redundant with structured fields.

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 listing return fields, and annotations carry the safety profile. It stops short of explaining pagination (smeshchenie/limit cap of 20), but the schema covers those adequately, so the gap is 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?

Schema coverage is 83%, so the baseline is 3, but the description adds meaning: it explains what zapros matches (model, series, color, type examples), how razdel scopes results, and clarifies the cena_ot semantics per leaf for doors. That goes beyond the field-level schema text.

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 (поиск) and resource (двери, погонаж, фурнитура) and clarifies the search semantics ('как в поиске на сайте'). It implicitly differentiates from razdely/tovar by being the keyword+filter search, but never names a sibling 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 description implies when to use it (free-text by model/series/color, within a section, with a price range), which maps to the params. It gives no explicit when-not or guidance on choosing between this and razdely/tovar, leaving that inference to the agent.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real value beyond them: it discloses that the returned price is cart-equivalent, that availability with lead time ('под заказ со сроком') is included, and that delivery/measurement/installation costs are not part of the figure.

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

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

Three short sentences, front-loaded with the core purpose and returns, and the exclusion clause is compact. The opening sentence is somewhat dense with clauses ('так же как в корзине сайта') but nothing is 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?

With no output schema, the description correctly spends a sentence on what comes back (product link with the selected variant) and on availability status. It does not state price currency/format or how the lead time is expressed, a minor residual gap for a pricing 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 75%, so most parameters are already documented in the schema, and the description only gestures at 'выбранными допами и количеством' without adding meaning beyond the schema's own 'по одному варианту на доп' note. Baseline 3 is appropriate given the schema does the heavy lifting.

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 (price calculation for a product with selected extras and quantity), mirrors the site cart for fidelity, and explicitly distinguishes scope by excluding delivery, measurement and installation while pointing to the sibling tool usloviya for those. An agent can tell this apart from tovar/poisk/razdely without opening a 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?

Clear context for when this applies (price of a configuration plus its availability) and explicit exclusions with a redirect to usloviya. No explicit statement about what to call instead when the user only wants a price without extras or availability, so it stops short of full routing guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds that the tool is scoped to one specific site's catalog and that its output feeds poisk, which is useful context. It does not describe the return shape (names vs. slugs, count), leaving a 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?

Front-loaded with the resource and site, then a compact enumeration, then the one actionable instruction about poisk. The category list is long but every item earns its place by telling the agent what coverage to expect; nothing is 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 zero-parameter, read-only discovery tool this is close to adequate, and the enumeration substitutes for a brief return-value description. However, with no output schema, the description never states the format of what comes back (a list of section names, slugs, or objects), which matters because those values are meant to be passed to poisk.

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 the baseline is 4. The description mentions a 'razdel' field, but explicitly attributes it to poisk rather than to this tool, so it clarifies cross-tool data flow rather than creating false parameter expectations.

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?

Names the specific resource (catalog sections of profildoors-dver.ru) and enumerates the actual section families returned: in-stock doors, interior doors by series/finish, Invisible hidden doors, opening systems, entrance doors, mouldings and hardware. An agent can tell this is a category-listing tool and not a product search, though the verb is implicit (it restates the title 'Разделы каталога' rather than saying 'returns the list of sections').

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?

'Поле razdel передайте в poisk' explicitly routes the agent to the sibling tool and states what to do with the result, which is the key workflow decision. It stops short of saying 'call this first to discover valid razdel values before calling poisk', which would make the ordering unambiguous.

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?

Аннотации уже сообщают readOnlyHint, idempotentHint и destructiveHint=false, поэтому описание не обязано повторять безопасность. Оно добавляет содержательную информацию о возвращаемых блоках: варианты с ценой и наличием, допы с ценами для выбранного варианта, а также смысл полей obyazatelnyy и komplektnost.

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?

Описание плотное, без явной воды, и начинается с главного — «Всё о товаре». Однако это одна длинная конструкция с несколькими вложенными перечислениями, которую можно было бы структурировать яснее.

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?

Для read-only инструмента без output schema описание достаточно раскрывает состав ответа и доменные поля. Схема полностью документирует входные параметры, а аннотации покрывают поведенческую безопасность; не хватает лишь явного указания на ошибки или взаимодействие id/url.

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?

Покрытие описаний параметров в схеме 100%, поэтому базовая оценка — 3. Описание немного усиливает смысл variant_id, уточняя, что цены допов показываются для выбранного варианта, но не добавляет формата или дополнительных ограничений по id/url.

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?

Начинается с «Всё о товаре» и перечисляет, что возвращается: описание, характеристики, варианты, допы с ценами. Это ясно определяет ресурс и объём данных, но не содержит глагола и явно не противопоставляет инструмент соседним poisk/raschet.

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?

Нет указаний, когда использовать этот инструмент вместо poisk или raschet. Фраза «Всё о товаре» лишь подразумевает сценарий полной карточки, но не задаёт условие выбора или ограничения.

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, openWorldHint=false, and destructiveHint=false, covering the safety profile. The description adds no behavioral context beyond the topic list: it does not explain that the tool returns reference text, how topic selection behaves, or any other trait beyond what annotations and schema already provide.

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 comma-separated list with no lead-in statement. It is not verbose, but the lack of structure and front-loaded purpose statement makes it less effective than it could be.

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 required enum parameter, full schema coverage, and annotations that carry the safety profile. The description lists all covered topics, which is adequate for topic selection, but it omits an explicit statement of what the tool returns and how to use it relative to sibling tools, leaving a gap for an agent deciding among alternatives.

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 enum parameter tema is fully documented in the schema. The description repeats the topic names but adds no mapping, syntax, or meaning beyond what the enum already provides, so the baseline score 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 enumerates the topics the tool covers (delivery, measurement, installation, warranty, payment, ordering, etc.), which implies it is an information-retrieval tool for store conditions. However, it never states an explicit verb or says that it returns store policy/reference information for the selected topic, and it does not distinguish itself from siblings like poisk, razdely, or tovar.

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 on when to use this tool versus alternatives. The topic list suggests it is for store-condition questions, but the description does not name any sibling tool, exclusions, or selection conditions.

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