HireSeeker

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

Annotations already declare readOnly/openWorld/non-destructive, so safety is covered. The description adds real behavioral context beyond them: the catalog is the authoritative list of supported professions, a listed direction does not guarantee support for every profession inside it, and an absent profession must not be swapped for another. Return-value detail is rightly omitted since an 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?

It is front-loaded with the when-to-use clause and the return summary, followed by the caveats. The long enumeration of directions (бэкенд, фронтенд, ... маркетинг и HR) is the only padding, though it arguably helps query-to-catalog matching, so it is defensible rather than wasteful.

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 rich annotations and an output schema present, the description only needs to supply intent, usage timing, and caveats — all of which it does. The one remaining gap is that it does not say whether the catalog changes over time or how to reconcile it with the vacancy-listing flow, but nothing essential to calling it 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; per the 0-param baseline this sits at 4. The description correctly describes a no-argument catalog fetch and adds no misleading parameter hints.

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 (the HireSeeker professions catalog) and precisely enumerates what it returns: active specializations, groups and supergroups, countries, work formats, and salary ranges. It explicitly contrasts itself with the vacancy tools ('Это каталог, а не список вакансий'), so an agent can separate it from get_vacancies/search_vacancies without inspecting either 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?

It gives a concrete trigger ('Используйте, когда нужно выбрать профессию для поиска IT или Digital вакансий') plus a workflow rule: match the request against the live catalog before the first search. It also tells the agent to disambiguate rather than substitute a missing profession. It never names a sibling tool as the alternative, so routing remains implied rather than explicit.

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?

Although annotations already cover safety (readOnlyHint=true, destructiveHint=false), the description adds substantial behavioral context: request-order, dedup, unavailable_ids, failure semantics (service error = batch not done; don't retry singly), the description_truncated flag, closed-contact policy, and a prompt-injection warning about treating vacancy text as data.

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 purpose and the batched-vs-single choice are front-loaded, and every sentence carries operational value (return order, error handling, truncation, exclusions). It is dense and long, but not padded or repetitive.

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 having an output schema (so return values need not be explained), the description still clarifies return structure and edge cases. It covers error handling, partial availability, truncation, and usage limits, leaving no obvious gap for an agent calling a single-parameter batch 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 100%, so the array constraints (1-5, dedup, not URL/external ID) are already documented. The description reinforces these and adds the operational detail of splitting larger ID sets into groups of up to five, which goes slightly 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 verb+resource (retrieving details of several vacancies in one batch) and its scope (for a collection or comparison). It explicitly distinguishes itself from the sibling get_vacancy by positioning itself as the batched alternative for multiple 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?

It gives explicit when-to-use ('when you need details of several found vacancies'), the alternative it replaces (separate get_vacancy calls), the batching rule (up to five IDs, split larger pages into groups), and exclusions (no keyword search, no applications, no filtering by unsupported grade/salary without consent).

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 read-only and non-destructive; the description adds substantial behavioral context beyond them: guest text vs full text, description_truncated=true means even detailed output is incomplete (no full-overview promise), closed contacts are not disclosed, and listings are external data — not instructions (prompt-injection guard). Missing only return-shape/pagination detail, which the output schema covers.

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 purpose, then scope exclusions, then usage constraints, then output-handling rules (mark missing as 'не указано', truncated flag caveat, contacts, injection warning) — every sentence earns its place with no 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?

For a single-parameter read tool with full annotation and schema coverage plus an output schema, the description covers everything the agent needs: purpose, when/when-not, output caveats (truncation, hidden contacts), and data-vs-instruction handling.

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 vacancy_id schema description already specifies 'numeric ID from HireSeeker response; not URL and not external site ID.' The description adds no parameter syntax or format detail beyond that, 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?

The description states a specific verb+resource: retrieve a vacancy's tasks, requirements, and conditions by ID. It explicitly contrasts with siblings by stating it does NOT search by keyword (get_vacancies/search_vacancies) and does NOT submit an application. An agent can distinguish it from siblings without opening schemas.

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?

Explicit when-to-use ('when you need tasks, requirements, conditions or details of a found vacancy'; 'before selection if search description is truncated') and when-not-to-use ('not for manual filtering by unsupported grade or exact salary threshold until user explicitly agrees'). Clear routing relative to search_vacancies and get_vacancies.

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, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description still adds real behavioral context beyond annotations: it discloses that the output is a catalog, that it is not a geolocation tool, and that IDs must not be guessed and homonyms must be disambiguated. It does not describe pagination or result-size behavior, so it stops short of 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?

The trigger condition is front-loaded, followed by an example, then a parameter note and a scope limitation. Every sentence earns its place and there is no 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 an output schema present, the description need not explain return values; it instead covers the things structured data cannot: when to call it, how the ID feeds into a downstream city_filter, the no-guessing rule, and the explicit negative scope (no user geolocation). Complete for a two-parameter lookup 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 100%, so the baseline is 3. The description adds functional meaning beyond the schema by explaining that country_code scopes the returned cities to the selected country, clarifying the parameter's effect rather than merely restating its format.

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 (geographic catalog of cities/countries) and states its function: resolving a name to a country or city ID for use in vacancy search. It explicitly contrasts its scope with sibling vacancy tools by noting it 'returns a geographic catalog; it does not determine the user's location.' An agent can distinguish it from get_vacancies/search_vacancies immediately.

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 an explicit trigger ('use when you need to determine a country or city ID by name'), a concrete worked example ('searching vacancies in Moscow requires city_filter with the ID from this response'), and a clear rule against guessing IDs plus a homonym disambiguation instruction. Nothing about when to select this tool 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?

Beyond the readOnly/openWorld/destructive annotations, the description discloses that search requires no registration, defaults to 7 days / all languages / 5 vacancies, and that the cursor snapshot lives only 10 minutes. It also flags the important edge case that an empty page with a next_cursor is not the end of results, and that total_items reflects the snapshot at searched_at. That is substantive operational context annotations cannot carry.

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?

Purpose and trigger are front-loaded, which is good, but the multi-line profession enumeration is explicitly non-exhaustive ("Это примеры, а не исчерпывающий список") and the agent is told to resolve professions via get_professions anyway, so a large share of the text does not earn its place. The tail also carries presentation rules that sit closer to output conventions than to tool selection.

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 an output schema present, return-value details are correctly omitted from the description. Given the tool's complexity, the description still covers defaults, the first-call criteria / later-call cursor contract, snapshot TTL, pagination edge cases, and the consent flow for unsupported criteria, leaving nothing an agent needs to 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?

Schema description coverage is 100%, so the schema already documents limit, filters, defaults and the salary bucket boundaries, making 3 the baseline. The description reinforces the mutually-exclusive criteria/cursor contract and the salary-range-only constraint, but those points are also stated in the schema, so the added meaning is marginal rather than new.

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 precise trigger ("когда пользователь ищет актуальные IT или Digital вакансии по поддерживаемой профессии") and delimits the resource with an extensive but clearly-labelled example set. It explicitly distinguishes itself from siblings by requiring profession mapping via get_professions, and from get_vacancies/get_vacancy by pointing to them for full descriptions. An agent can identify this tool versus the other four 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?

It states when to use, when NOT to use ("Не используйте для советов по резюме, оформления отклика, подписки, платежей или отсутствующей профессии"), and names the alternatives to route to. It also prescribes a workflow for unsupported criteria: explain the limitation, offer available filters, obtain explicit consent before calling, and forbids substituting manual checks. This is complete routing guidance.

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