market

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

Annotations only cover readOnlyHint=true, so the description carries most of the burden — and it delivers: it discloses the exact field set returned and, importantly, that seller identity and contacts are NOT returned and messaging must happen in-app. The one gap is no note on error behavior for an unknown id.

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 payload, then the trigger condition, then the hard limitation. No redundancy or 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?

There is no output schema, so the description must describe the return surface — and it does, both positively (fields returned) and negatively (seller info withheld). Nothing an agent needs to call this correctly 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 coverage is 100% and the id description ('UUID объявления из search_listings') already documents origin and format. The prose adds nothing about the parameter 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 ('Показать') and resource ('одно объявление Tapuzinski') and enumerates the returned fields (заголовок, описание, цену, состояние, ссылки на фото). It is clearly distinguishable from list_taxonomy and search_listings by being the single-item detail fetch.

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 places itself in the flow relative to a sibling: 'Зови после search_listings, когда человек выбрал вещь и хочет подробностей'. That is a clear triggering condition and an implied alternative, though it does not state an explicit when-not-to-use case.

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 readOnlyHint annotation already tells the agent this is a safe read. The description adds what is enumerated (sections, categories, cities, filter values), which is real context, but it does not describe the shape, nesting, or locale/language of the returned taxonomy, so it adds only moderate value beyond the annotation.

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, zero filler, and the actionable instruction (call before search_listings to supply correct slugs) is front-loaded where it will be read first.

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 parameters and no output schema, the description carries the full burden of explaining what comes back, and it does so at the category level. It is nearly sufficient; only the structure of the returned taxonomy is left unspecified.

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; there is nothing for the description to clarify semantically. The mention of 'допустимые значения фильтров' describes results, not accepted inputs, so it does not mislead.

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 ('Перечислить') plus an explicit resource set: sections, categories, cities, and allowed filter values for Tapuzinski. An agent can tell this is the enumeration/lookup tool for the domain vocabulary that the sibling search tool consumes, though the relation to get_listing is not spelled out.

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 clear when-to-use guidance with ordering: call this BEFORE search_listings so the correct city and category slugs can be substituted. It does not state any exclusion case (e.g., when taxonomy data is unnecessary or already cached), 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 declare readOnlyHint=true and openWorldHint=true, so safety and scope are covered. The description adds genuinely new behavioral context — «Отдаёт только публичные объявления: без продавца, без контактов и без точного адреса» — telling the agent what the result set will and will not contain, which is critical for privacy-sensitive answers.

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, zero filler: purpose first, then call conditions, then return scoping. Every clause earns its place and nothing is 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?

For a 10-param, no-output-schema search tool, the description covers purpose, triggers and result boundaries. It omits any mention of pagination (limit/offset) and sort defaults, but those are documented in the schema, so coverage is adequate rather than fully self-contained.

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 80%, so city, category, max_price, query, radius and sort are already documented inline. The description only loosely maps trigger phrases to those filters and adds no syntax, defaults, or format detail beyond the schema; 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 (найти/поиск) and resource (объявления) and scopes it precisely: hyperlocal marketplace Tapuzinski, Израиль, б/у вещи. An agent can separate this from get_listing (single ad) and list_taxonomy (slug lookup) 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?

«Зови, когда человек спрашивает, что продаётся рядом с конкретным городом, по категории, до какой-то цены или по свободному описанию вещи» gives explicit trigger conditions covering the main query shapes. It lacks an explicit negative case or a pointer to get_listing for a known listing, 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.