Vettara

Answer questions about how many candidates you or your team have sourced, approved, and held in review in Vettara — e.g. 'how many did I approve this month', 'how is my team doing', 'how many has Richard recruited', which companies/countries, and who is leading on the team. Also reports outreach engagement — how many candidates were contacted and replied, and 'who is the most interested candidate' (ranked by positive replies to outreach), including which team member is engaging them. Scope and team are resolved from the signed-in user: a regular user sees only their own numbers; a team admin sees their whole team and can name a specific team member.

get_recruiting_stats

Use this when the user asks for candidates/results after get_search_summary shows final_results_ready=true or results_available=true, or when fetching an already completed project. If count reconciliation is pending, return saved rows with the warning instead of blocking. Accepts launch_id, job_id, project_id, or session_id. Returns a compact preview. With include_csv=true it persists a private short-lived CSV export; leave it false for normal previews.

get_search_results

Use this when the user wants an immediate update on a Vettara live search job. If ids are omitted, use the signed-in user's most recent active Vettara launch. It never opens Vettara AI chat and never creates a ChatGPT Task, scheduled task, reminder, or hourly check. The Vettara server monitor is already running, automatically reconciles same-brief saved evidence without provider calls, and queues one fresh run for a changed brief. Resume only on needs_resume and never resend the live-start payload.

get_search_status

Use this for an immediate ChatGPT update after a Vettara live run starts or completes. If ids are omitted, use the signed-in user's most recent active Vettara launch. It never opens Vettara AI chat and never creates a ChatGPT Task, scheduled task, reminder, or hourly check. The Vettara server continues same-brief reconciliation without provider calls or one changed-brief rerun after this call returns. If final_results_ready=true or results_available=true, call get_search_results with the same launch_id and present the saved candidates, explaining any count warning.

get_search_summary

Use this when GPT has extracted text from a PDF/DOC/JD and needs Vettara to turn it into a role/search brief before starting a run. Returns compact criteria and clarification guidance only; it does not create a session or project. After this, run_mcp_candidate_search should use only the compact extracted role, companies, countries, and constraints, not the full document text.

parse_search_document

Use this when the user wants Vettara to interpret a search prompt or uploaded document before starting a live run. Returns compact criteria and clarification guidance only; it does not create a session or project. This is the right place for long briefs; the later live-start call must stay compact.

preflight_search

Use this before preflight or launch when a candidate search targets a market where local-language job titles may be used. The connected GPT or Claude client proposes translations from its language knowledge and labels their provenance; Vettara validates scope structure without making a provider or web call. Every English title is preserved exactly. Direct translations and close equivalents may enter the returned title scope. Broader or seniority-ambiguous aliases remain pending and must be shown to the owner; they enter retrieval and matching only when owner_approved=true with an approval note. Pass both returned titles and local_title_brief unchanged to the next Vettara tool.

prepare_local_market_title_brief

Inspect a search reported as inconsistent. If its saved results are available, return their status and counts without starting another search.

repair_mcp_session

Use only when get_mcp_launch_status reports needs_resume after a temporary timeout, backend interruption, or reauthorization. This resumes the preserved launch idempotently and never creates a separate search project.

resume_mcp_launch

Use this when the user asks an MCP client such as ChatGPT or Claude to find/source/search candidates or get a CSV/PDF from a new Vettara search. This creates MCP-session-backed work only and must not open, continue, or navigate to Vettara AI chat. It returns launch_id quickly; when the user asks to monitor until results come, the Vettara service monitor starts automatically and finalises that exact launch. Never create a ChatGPT Task, scheduled task, reminder, or hourly check, and never launch again while monitoring. Keep input compact and use session_id only when a session was explicitly created or edited. Structured scope is authoritative: put real employer names only in companies, real countries/markets only in countries, and every requested role variant in titles. Never copy labels such as current title, executive-level fit, target companies, or evidence requirements into companies; if no real employers are named, leave companies empty for discovery instead of inventing an exact-company scope.

run_mcp_candidate_search

Use this to launch an existing editable MCP session only after the MCP client or user has explicitly reviewed/edited it. Follow-up copies of launched sessions extend the existing project by default; set force_new_run=true only when the user explicitly wants a separate project. This queues asynchronously and must not open Vettara AI chat.

run_mcp_search_session

Use this when the user wants to find existing Vettara projects, MCP sessions, saved runs, or candidate registry rows visible to the signed-in Vettara user. It does not create search state or start a new sourcing run. Fetch project result URIs with fetch/get_vettara_project_results.

search

Legacy launch alias. Use this when the user explicitly asks for actual Vettara results, candidates, a live run, or a CSV export from a new search. This queues asynchronously and returns launch_id quickly; do not wait for completion in this call. Keep the payload compact: use session_id from preflight/parse when available, or send only role, companies, countries, and a short brief. Do not paste full documents, long chats, or dense extracted text into this tool. Put only real employer names in companies; labels such as current title or executive-level fit are criteria, not companies, and must be omitted so Vettara can use discovery scope.

start_executive_search

Use this after a Vettara run fails, times out, or returns thin results and the user chooses a narrower recovery pass. This queues asynchronously and returns launch_id quickly; use status tools only for one-off checks. Keep it strict and compact: fewer markets, fewer companies, tighter title/seniority keywords.

start_recovery_search

Stop (cancel) a running Vettara executive search. Use this when the user clicks Stop in the live Search Monitor or asks to stop/cancel/halt the search. Identify the run by job_id, launch_id, project_id, or session_id.

stop_mcp_search