hr

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

No annotations are provided, so the description carries the full burden. It discloses a key behavioral trait: 'Сервер отдаёт релевантные данные — вывод формирует ассистент' (the server returns data, the assistant forms the output), indicating the tool is read-only and returns raw material rather than a final answer. This goes beyond the tool name and helps the agent 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 two short sentences (one Russian, one English), immediately stating the tool's purpose and behavior. It avoids redundancy and every clause adds value, making it highly efficient.

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 with only two parameters and no output schema. The description sufficiently explains the interaction model (server returns data, assistant formats response) and the purpose. The only minor gap is not explaining how the optional 'candidate' parameter affects behavior, but that is covered 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% for both parameters, with clear descriptions for 'question' and 'candidate'. The tool description itself adds no additional parameter-level detail beyond what the schema already provides, so the baseline 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 clearly states the tool's function: asking a specific question about a candidate's experience, with concrete examples ('работал ли с X?', 'что делал в Y?'). It distinguishes itself from siblings like get_resume or get_profile by focusing on ad-hoc targeted queries rather than whole-document retrieval.

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 phrase 'Точечный вопрос' (targeted question), suggesting it's for specific fact-finding rather than broad overviews. However, it doesn't explicitly mention when not to use it or name alternative tools from the sibling list, so guidance remains implicit 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?

With no annotations, the description carries the full burden of behavioral disclosure. It adds some context (e.g., 'кандидат загрузит решение файлом' and status returns a download link), but it does not mention side effects like email sent, required permissions, error cases, or the exact response structure. This is a minimal but adequate level of transparency.

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 compact two-sentence bilingual text that front-loads the core action ('Тестовое задание кандидату' / 'Send a take-home assessment'), then efficiently lists the action-specific parameters. Every word contributes value, with 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?

The tool has no output schema and moderate complexity (two actions, seven parameters). The description mentions that status returns a download link and implies that send returns an assessmentId (via the parameter description), but it does not explicitly describe the response format for either action. This gap is noticeable but not critical for a relatively simple 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?

The schema description coverage is 100%, with each parameter already annotated with action-specific context (e.g., '(send)' and '(status)'). The description reinforces which parameters are needed for each action, but this adds little beyond the schema. Baseline 3 is appropriate because 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?

The description clearly states the tool's purpose: 'Send a take-home assessment or check its status and download link.' It uses specific verbs ('send', 'check') and a specific resource (assessment), and it distinguishes itself from sibling tools like send_vacancy and message_candidate by focusing on assessments.

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 provides clear usage context by breaking down the two actions (send and status) and listing the required parameters for each: 'action=send — отправить (нужны title, body, recruiterContact)' and 'action=status — статус и ссылка на скачивание решения (нужен assessmentId).' It does not explicitly name alternatives, but the use case is sufficiently clear to guide selection.

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?

No annotations are provided, so the description carries the behavioral transparency burden. It discloses the exact categories of data returned (salary components, deal-breakers, notice period, etc.) and the language selection behavior with a default of ru. It does not mention failure modes or access requirements, but for a read-only data retrieval tool this is fairly transparent.

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 compact bilingual statement with no filler. Each sentence contributes either to defining the output scope or clarifying the language parameter. It is well structured and easy to parse.

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?

Given that there is no output schema, the description adequately lists the expected data categories, includes language options, and mentions candidate optionality through the schema. It is sufficiently complete for an agent to select and invoke the tool correctly, and the bilingual format ensures accessibility.

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 already covers both parameters with 100% description coverage. The tool description adds value by specifying that lang defaults to ru, and it clarifies the meaning of the 'candidate' through the returned data categories. This goes slightly beyond the schema's baseline.

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 explicitly states the tool returns the candidate's terms for employment: compensation expectations, notice period, work format, location, visa, etc. This is a specific resource with clear scope and is easily distinguished from sibling tools like get_profile, get_references, and get_resume, which cover different data facets.

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 clearly implies when to use it: whenever you need a candidate's conditions for starting, such as salary, timeline, work format, or location. It provides a useful context for usage, though it does not explicitly name alternatives or exclusions compared to sibling tools.

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 no annotations, the description carries full responsibility. It discloses the key behavioral constraint (must introduce via recruiter_context first), which is valuable. However, it does not mention what happens if the prerequisite is unmet (e.g., error vs. empty response) or any other behavioral details like rate limits, leaving gaps.

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 concise, only two sentences, with the core purpose front-loaded. The bilingual repetition (Russian and English) is slightly redundant but understandable for a multilingual environment; overall, it is efficient and well-structured.

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 tool with one optional parameter and no output schema, the description covers purpose, prerequisite, and even the content of the contacts (phone, email, messengers). It lacks failure-mode details, but it is largely complete for a straightforward retrieval operation.

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 already provides 100% coverage for the single candidate parameter, including its slug source and optionality in personal mode. The description adds no extra parameter context beyond what the schema states, so the baseline 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 clearly specifies that the tool provides direct candidate contacts (phone, email, messengers), which is a distinct resource. It differentiates from sibling tools like get_profile or get_resume by focusing solely on direct contact information.

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 states the prerequisite that contacts are only given after introducing yourself via recruiter_context, which is clear usage context. It does not mention alternatives or exclusions, but the condition is sufficient for an agent to know when to invoke this 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?

No annotations are provided, so the description must convey behavioral traits. It implies a read-only retrieval (getter), but does not explicitly state that no modifications occur, nor does it mention error conditions or output format. The schema covers the prerequisite of the candidate slug, but the description alone is not deeply transparent.

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 very short and front-loaded with the main message. It includes both Russian and English versions, which is slightly redundant but not harmful. Every sentence earns its place, though the bilingual repetition could be trimmed.

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 retrieval tool with optional parameters and no output schema, the description is minimal but adequate. It conveys the core function but lacks details about return value structure, localization behavior, or handling of missing candidates. Given the tool's simplicity, a score of 3 is appropriate.

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 input schema provides detailed descriptions for both 'lang' and 'candidate' (100% coverage), so the baseline is 3. The tool description adds no additional information about parameters, relying entirely on 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 clearly identifies the resource as 'Candidate's answers to common recruiter questions' and directs the agent to 'check here before writing to him,' implying retrieval. It distinguishes from sibling tools like get_resume or get_profile by focusing specifically on FAQ answers.

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 phrase 'check here before writing to him' provides explicit context for when to use the tool: before composing a message to the candidate. It does not name alternatives or exclusions, but the usage context is clear and actionable.

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?

No annotations are provided, so the description carries the burden. It discloses what the profile includes and that lang defaults to ru, but does not mention auth requirements, error behavior, or whether it is read-only. Adequate for a simple read operation but not rich.

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 compact sentences in both Russian and English. The bilingual approach is slightly redundant but serves clarity for different locale users; no wasted words.

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 low-complexity tool with two optional parameters and no output schema, the description fully covers the profile contents and language behavior. It is a complete, self-contained explanation.

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 baseline is 3. The description adds value by stating the lang default (ru) and clarifying that the candidate parameter is optional in personal mode, which supplements the schema's default of null.

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 it provides a candidate overview with specific fields (name, city, summary, links). It distinguishes from siblings like get_resume and get_contacts by labeling it the starting point for acquaintance.

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 Russian phrase 'Начните знакомство отсюда' (Start acquaintance here) explicitly tells when to use this tool, implying it is the initial step. It does not explicitly list when not to use alternatives, but the context 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?

With no annotations, the description carries the transparency burden. It adds useful behavioral context by noting that references are collected with consent ('с их согласия') and positioned before an offer, but it does not disclose output format, whether the call is read-only, or any limitations.

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 compact, front-loaded with the core content, and the bilingual redundancy is minimal. Every phrase adds value: source of references, consent, and use case.

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 one-parameter tool with no output schema, the description covers purpose, source, consent, and timing. It could be slightly more explicit about what the returned references contain, but the tool name and description make this reasonably clear.

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 fully documents the single parameter with description and usage guidance about null/personal mode, so the schema provides the needed semantics. The description itself adds no parameter details, which is acceptable given 100% schema coverage.

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 tool as providing references about a candidate from former colleagues and managers, with a specific use case ('trust-сигнал перед офером'). This distinguishes it from sibling tools like get_resume or get_contacts, even though the description uses a noun phrase rather than an explicit verb.

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 explicitly frames the tool as a pre-offer trust signal, giving clear usage context. It does not list alternatives or exclusions, but the purpose is specific enough to guide selection among 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?

With no annotations provided, the description carries the full burden for behavioral disclosure. It describes the content returned but does not mention read-only nature, error handling, or any prerequisites. However, the name 'get_resume' strongly implies a safe retrieval, and the schema covers the default behavior, so some transparency is inherent.

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 concise, consisting of a short content summary and a usage hint in two languages. Every sentence earns its place, and it is front-loaded with the core purpose. No wasted words.

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 retrieval tool with no output schema, the description adequately explains what the tool returns (work history, achievements, skills) and provides a usage hint. It is complete enough for the tool's complexity, though it could mention edge cases like null resumeId handling, which the schema already partially covers.

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%, with both resumeId and candidate parameters already described in the schema. The description adds no additional meaning about parameters, so the baseline of 3 is appropriate—the schema handles parameter semantics fully.

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 tool returns a full candidate resume, listing work history, achievements, and skills. It uses a specific noun phrase that conveys the resource and distinguishes it from siblings like get_profile or get_contacts, though it lacks an explicit verb like 'get' or 'retrieve'.

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 phrase 'Start here if you need the full picture' gives a clear context for when to use the tool, but it does not mention alternatives or explicitly state when not to use it. This is useful but less explicit than naming sibling tools or exclusions.

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?

No annotations are provided, so the description carries the behavioral burden. It discloses the three distinct behaviors and their required inputs, plus optional notes (notes, reason, durationMinutes) and source info (conversationId from message_candidate). This covers the core behavioral states well. It misses a few implicit details—e.g., whether cancel is destructive or idempotent, or the exact effect of reschedule—but the action-focused transparency is strong.

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 compact, with a Russian imperative opening and a bilingual action list. The structure is front-loaded with the core verb and resource, followed by an efficient mapping of actions to required params. It loses one point because the English summary at the end ('Propose, reschedule or cancel an interview...') repeats what the Russian already states, adding slight redundancy.

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?

Given 11 params, no output schema, and no annotations, the description does a solid job covering the main operational logic: three actions, their required fields, and optional parameters. It is nearly complete for selecting and invoking the tool. The main gap is that it doesn't specify the return value/outcome after each action (e.g., what a successful propose/cancel returns), but the absence of an output schema is partially compensated by the action-parameter clarity.

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% (every parameter has a description). The description adds value by grouping parameters by action, which the schema alone doesn't convey. For example, it clarifies that companyName is only for propose and conversationId is needed for reschedule/cancel. This action-parameter alignment goes beyond the schema's individual field descriptions, so it earns a score above baseline.

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 'Назначить кандидату интервью и управлять им' (assign an interview and manage it) and enumerates three actions: propose, reschedule, cancel. This is a specific verb+resource combination and distinguishes itself from siblings by covering the full interview lifecycle. However, it loses a point because the bilingual split (Russian action list, English summary) adds slight redundancy and doesn't explicitly contrast with sibling tools.

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 provides explicit per-action guidance: which parameters are needed for propose (companyName, proposedSlots, channel, interviewType, recruiterContact), for reschedule (conversationId, proposedSlots), and for cancel (conversationId). This is effectively a usage map, giving clear when-to-use instructions and parameter selection criteria. It doesn't explicitly name alternative sibling tools, but the action breakdown makes usage unambiguous for a multi-action 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?

No annotations are provided, so the description carries the full burden. It does disclose the output structure (matched skills, seniority, exit conditions), which is helpful. However, it doesn't mention whether the operation is read-only, how the candidate is used when provided, or any edge cases. Given the low risk of a text-analysis tool, this level of transparency is adequate but not thorough.

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 sentence with a bilingual equivalent (Russian and English), concise and upfront. Every word earns its place, clearly stating the action and expected output without any fluff or redundancy.

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?

Given the tool's moderate complexity (3 params, no output schema, no annotations), the description is fairly complete. It names the key output components (skills, seniority, exit conditions), giving the agent a reasonable expectation of the return values. It does not explain the optional candidate behavior or language parameter, but those are covered in the schema. For a read-only analysis tool, this is adequate.

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 input schema already provides descriptions for all three parameters (lang, candidate, vacancyText) with 100% coverage, so the description adds no additional parameter meaning. It indirectly references vacancyText ('paste a job description') but doesn't clarify lang or candidate nuances beyond the schema. Baseline 3 is appropriate because 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?

The description clearly states the tool's function: 'Paste a job description to evaluate candidate fit' (or in Russian: 'Вставьте текст описания вакансии — получите структурированную оценку соответствия'). It specifies the resource (job description) and the action (evaluate fit), and lists specific output components (matched skills, seniority, exit conditions), which distinguishes it from broader sibling tools like 'assessment'.

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 usage is implied: paste a job description to get a fit evaluation. However, there is no explicit guidance on when to use this tool versus alternatives like 'assessment' or when not to use it. The schema mentions the candidate slug from search_candidates but the description doesn't explain the optional candidate context or any prerequisites. Thus, it provides implied usage but lacks clear alternatives or exclusions.

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 no annotations, the description must carry the burden of behavioral disclosure. It reveals that the candidate answers in a messenger ("кандидат отвечает в мессенджере"), implying asynchronous interaction. However, it does not mention prerequisites for creating a new thread (e.g., subject and recruiterContact) or describe the outcome of sending a message. Some of this is covered by the schema, but the description adds limited behavioral context beyond the mode definitions.

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 concise and well-structured. It opens with a clear purpose, then uses a conditional structure to explain the three modes in a single sentence, followed by a brief English summary. Every sentence contributes necessary information with no redundancy.

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 has 5 optional parameters and no output schema, and the description covers the primary use cases (list, read, send). It does not explicitly document how to start a new thread (requiring subject and recruiterContact), but that information is present in the schema. The description is adequate for the tool's moderate complexity, though a bit more detail on thread creation would make it fully 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?

Schema coverage is 100% with per-parameter descriptions. The description adds value by explaining how parameters combine to trigger different modes: absence of text/conversationId lists threads, presence of conversationId reads history, and presence of text sends a message. This interplay is not fully captured by the individual schema descriptions, so the description meaningfully enhances parameter understanding.

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 tool's purpose: "Переписка с кандидатом" (correspondence with candidate) and enumerates three distinct modes: list threads, read thread history, and send a message. This specific verb-resource combination and the explicit modes distinguish it from sibling tools like get_profile or send_vacancy.

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 provides clear context on how to invoke each mode: "Без параметров text/conversationId — список тредов; с conversationId — история треда; с text — отправить сообщение". It does not explicitly discuss alternatives or when not to use the tool, but the mode-based guidance makes the usage conditions 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?

With no annotations, the description must carry the transparency burden. It discloses that the candidate will see the recruiter's info and that contacts become available, which is a useful behavioral side effect. However, it doesn't mention persistence, reversibility, or error conditions, so transparency is only partial.

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 short sentences with a translation, front-loaded with the core action 'Представьтесь'. Every word earns its place, and the structure is both concise and clear.

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?

Given the tool's simple context-setting role, the description adequately explains the main workflow: introduce yourself to unlock contacts. It doesn't explain optional parameters like 'candidate' or 'notes', but the schema covers them. The description is complete enough for the tool's purpose.

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%, providing a baseline of 3. The description adds value by specifying that the email must be the one used to log in ('email, под которым вошли'), which clarifies the email parameter beyond the schema's 'key for lead'. It also hints at the role of company/name/role in the introduction.

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 tool's purpose: introduce yourself (company, name, role) to unlock contacts. It references the sibling tool get_contacts, which distinguishes it from other candidate-facing tools. The verb 'Представьтесь' is specific and action-oriented.

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 usage: provide your email to unlock contacts, making this a prerequisite for get_contacts. It gives clear context but does not explicitly mention when not to use or name alternative tools beyond get_contacts.

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?

No annotations exist, so the description carries the burden. It discloses that the candidate receives a notification and can respond, and that the recruiter's email is auto-filled. This is useful behavioral info, though it omits other side effects like whether sending is irreversible or if there are any 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?

The description is concise and front-loaded, with the main action in the first phrase. It includes both Russian and English, which duplicates content but is not overly long. Each sentence serves a purpose.

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 no output schema, the description provides sufficient context for a send action: the candidate receives a notification and can respond. It covers the main behavioral outcomes, though it doesn't address error cases or the response format. Overall adequate for the tool's complexity.

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 explains all parameters. The description repeats some optionality (candidate, recruiterContact) but doesn't add significant new meaning beyond what's in the schema. Baseline 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 clearly states the tool sends a vacancy to a candidate ('Отправить кандидату вакансию'), distinguishing it from sibling tools like message_candidate. It also frames it as the 'first step' in the hiring process, adding context.

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?

Provides clear context on when to use it ('if he suits you') and clarifies that candidate and recruiterContact are optional in personal mode. However, it does not explicitly name alternatives or when not to use, so it's strong but not a perfect 5.

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