Витрина неликвида ГЮТЕ ТЕХ

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavior beyond annotations: the exact per-line result categories ('есть', 'артикул есть у марки X...', etc.) and instructions to show price, check date, and links to the user.

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 front-loaded with purpose, then usage, parameter handling, and output expectations. It is fairly dense but every section adds operational value; some details repeat schema descriptions, preventing 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?

There is no output schema, so the description appropriately explains both the per-line result states and how the agent should present results to the user. Combined with strong annotations and full schema coverage, the definition gives enough context to call and interpret the tool correctly.

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

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

Schema coverage is 100%, so the schema already documents article, brand, name, and qty. The description nevertheless reinforces required vs optional fields and adds practical semantic guidance for brand transliteration ('Mercedes-Benz, BMW, Hyundai/Kia — не «Мерседес»') and the 50-line batch limit.

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 and resource: 'Сверить список деталей с витриной неликвида'. It makes clear this is a batch list-checking tool, which is distinct from the sibling tools get_part and search_parts that imply single-part lookup/search.

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 explicitly says when to call it: 'Звать, когда у пользователя список запчастей, заказ-наряд, счёт или рекомендации по ремонту'. It does not name when-not to use it or explicitly contrast it with search_parts/get_part, so it falls short of the top score for 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 readOnlyHint, idempotentHint, and destructiveHint=false already supplied by annotations, the description adds useful behavioral context by listing the full shape of returned offers and noting that requests are handled externally by a human. It does not discuss pagination, limits, or authentication, but for a read-only lookup with no output schema it discloses enough to set 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 front-loaded with the resource and contents, followed by parameter sourcing guidance and a boundary note about external request submission. It is reasonably tight, though the enumeration of offer fields could be compressed if brevity were the priority.

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, so the description appropriately enumerates the returned offer fields and mentions the request link. It is complete for a two-parameter read-only detail tool, with only minor omissions such as pagination or result limits if they exist.

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. The description reinforces that brand_slug and article should come from check_parts or search_parts, adding provenance beyond the schema's brief field descriptions, especially for article. It does not otherwise add format or validation details.

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 the card of a non-liquid showcase position and enumerates exactly what it contains: all seller offers with price, quantity, shipping city, seller, reconciliation date, and condition notes. It also names sibling tools check_parts and search_parts as the sources for brand_slug and article, so an agent can distinguish this detail lookup from those search 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?

It gives explicit workflow guidance: take brand_slug and article from the responses of check_parts or search_parts. It also states that the linked request must be filled in by a human on the site, which sets a clear boundary on what the tool does not do. It does not explicitly say when not to use this tool versus the siblings, but the implied sequence is clear.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: a hard cap of 20 positions and the exact shape of each result (price, shipping city, seller count, verification date, links), which matters since there is no output schema. It does not explain pagination or how to reach results beyond the top 20.

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: what it does, what comes back, and where to go instead. The searchable fields and the result-shape summary are front-loaded ahead of the fallback routing, and nothing is 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 one-parameter read-only search with no output schema, the description covers purpose, query semantics, result fields, result cap and the sibling alternative. An agent has everything needed to call it correctly and to know when not to.

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% for the single query parameter, so the baseline would be 3. The description earns the bump by clarifying that the input is free-text keywords spanning three dimensions and by giving a concrete mixed-token example, which tells the agent it can combine brand and part name in one string.

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 (search listing positions on the clearance showcase) plus the exact query dimensions: part number, part name, brand. The example «колодки KTM 890» and the explicit contrast with check_parts let an agent distinguish it from both siblings 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?

Gives an explicit routing rule: for a list of parts or a work order, use check_parts instead. That covers the main confusion case, but the other sibling get_part is never mentioned, so the agent must infer when to switch from search to a single-part fetch.

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