Точечный вопрос про опыт кандидата: «работал ли с X?», «что делал в Y?». Сервер отдаёт релевантные данные — вывод формирует ассистент. / Ask a specific question about the candidate's background.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | Вопрос рекрутёра, до 1000 символов | |
| candidate | No | Slug кандидата (из search_candidates). В личном режиме не обязательно: отправьте null или не передавайте параметр. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It explicitly states that the server returns relevant data and the assistant forms the final output, which is an important behavioral disclosure about the tool's I/O contract. It does not discuss side effects or limitations, but being a question-answering tool, the disclosed behavior is sufficient.
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 and front-loaded with the core purpose, followed by examples and the data-flow note. The bilingual repetition takes a small extra space but is not wasteful and may aid multilingual agents.
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 two-parameter tool with no output schema, the description covers the purpose, the input type, and the expected behavior of the response. It is complete enough for an agent to know how to invoke it and what to do with the result, though it does not detail the exact format of the returned data.
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 semantic context about the type of question expected (specific, experience-focused, with examples), but it does not add much beyond what the schema already states for the question and candidate parameters.
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 one that asks a specific, targeted question about a candidate's experience, with concrete examples ('работал ли с X?', 'что делал в Y?'). This separates it from static retrieval tools like get_resume or get_profile and also distinguishes it from assessment or manage_interview by focusing on a pointed Q&A interaction.
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: use when you need a specific answer about a candidate's background rather than a full document or profile. It lacks explicit exclusions or direct sibling comparisons, but the examples and phrasing imply the appropriate situation for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct candidate resource or workflow step: profile, resume, conditions, contacts, FAQ, references, interview, assessment, vacancy matching, and messaging are clearly separated. Even similar get_* tools are differentiated by description, and ask_about_experience is explicitly a targeted query rather than a full document.
Most tools follow a clear imperative get_/send_/manage_/match_/message_ pattern, making the set predictable. The exceptions are 'assessment' and 'recruiter_context', which are noun-only names and break the verb-led convention, though the lowercase snake_case style is consistent throughout.
Thirteen tools is well within the ideal range for a recruiting-focused server. Each tool covers a meaningful step in the candidate engagement workflow, from initial context and profile retrieval to vacancy sending, matching, interviewing, and assessment, with no obvious bloat.
The core candidate lifecycle is well covered: viewing candidate information, contacting them, sending vacancies, matching against job descriptions, proposing interviews, and managing assessments. Minor gaps exist around post-assessment progression, explicit offer/rejection handling, and broader pipeline or status management, but agents can mostly work around these.