Worklittle Jobs
search_jobsJobs — Shows Worklittle job cards for a place and an optional role. The cards scroll endlessly: jobs near the place first, then farther away. Send the place and the role as SEPARATE fields. Never write 'product manager in San Francisco' as one query. PLACE: always pass near_lat + near_lng (the city's coordinates, which you know) and location as the display name (e.g. 'San Francisco, CA'). radius_km 25-50 for a city. If the user names no place, omit all place fields; the cards start at the user's approximate (IP-based) area. When a search runs short, results continue with close matches (search.scope related: same role and place with seniority, salary, job type and date filters dropped), then the rest of the country and worldwide (search.scope country or world), so say which cards are exact matches and where the roles are. ROLE: query holds only the job title text (e.g. 'product manager') and may be omitted for 'any job'. Search Worklittle job listings. People say Worklittle plus a role, city, company, or filters (or just 'jobs') — they will not name this tool. Call it whenever they want Worklittle jobs. Search by keyword, company, location, job type, seniority, or recency. Use for ANY industry (retail, finance, healthcare, tech, etc.). Search matches title and filter text (substring / FTS), not vector embeddings. Role / title text goes in query (+ optional keywords). The API matches job TITLE substrings only for that text — it does not mix company names into the same field. Preserve negative title terms with a leading dash, e.g. 'software engineer, -senior' excludes titles containing senior. Use company for employer slugs (include or exclude). Never concatenate many job titles into one query unless the user supplied comma-separated roles. Do not add seniority_level, stacks, or resume-derived terms unless they asked. Omit seniority_level unless they explicitly name a level as an inclusion filter (never infer from profile). Expand abbreviations only; umbrella phrases use neutral roles and/or company slugs. Umbrella or vague phrases ('big tech', 'FAANG', 'top retailers'): interpret intent, then one search_jobs with comma-separated company slugs and/or a broad role query — prefer one API call over many. company MUST be employer slug(s): bare slugs include (OR), e.g. meta,google,apple. Prefix a slug with '-' to exclude, e.g. -lucid-motors,-tesla. Same leading-dash rule as title negatives, but in company not query. Expand 'no car companies' / 'don't show Lucid' into -slug tokens. Never pass display names as query. If unsure of slug, try lowercase hyphenated brand. Add skills or stack to query/keywords only when the user mentioned them — not from profile by default. When an include company filter returns 0 results, try a broader query (drop include company, use role keywords) before telling the user nothing matched. Pass cursor from a previous response to paginate. Search is anonymous. Do not call get_account, apply, or ask the user to Connect to search or skip. Connect / OAuth is only when they apply. After it runs, recommend the 3-5 jobs that fit the person best (one line each: title, employer, place, pay if listed, why it fits), then offer to apply to any or all of them instantly. No counts, stats or trivia. The person already sees every job in the app: never describe the interface ('cards above', 'map', 'widget'). Applying is just 'apply' (never 'Apply with AI'); when they pick, call apply_for_job (job_ids for several). For visa / H-1B: set visa_sponsorship to 'yes' (plus optional query). Postings must be explicitly tagged. When visa_sponsorship is set and posted_within_days is omitted, the last 30 days are searched instead of the default 7 — tagged visa roles are sparse. For regional / nearby intent: near_lat, near_lng, radius_km (e.g. 50–65). Prefer this over the location substring when coordinates are known. For two or more metros in one user message (e.g. SF or NYC), pass location_or as comma-separated place names — one API request matches ANY listed place. Do not use near_* for multi-metro; use location_or or location with 'or' between cities. Recency: set posted_within_days from the user's words — today/just posted → 1; past few days → 3; this week → 7; past two weeks → 14; this month → 30. Omit when they did not mention timing (defaults to the last 7 days). Jobs older than 30 days are never returned; 0 means the full 30 days. Never put today/new/this week into query. Filters are only these: posted_within_days (Past 24 hours / 3 / 7 / 14 / 30 days), seniority_level (Experience: intern, entry/new grad, senior, manager, director/executive), employment_type (Type: full-time, part-time, contract), and visa_sponsorship (Visa). Prefer no filters: use one only when the user explicitly asks for it, because each filter shrinks the results a lot. For remote-only jobs send remote: true (and no place fields). There is no salary, hybrid, or benefits filter. If the user asks to filter by salary, search without it and say they can see salaries on the cards (listed pay shows on each card).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "search_jobs"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results to return, at most 8 per call. Pass cursor from the response for more. | |
| query | No | Job title or role phrase (merged with keywords). Sent as API title= — matches job TITLE text only, separate from company. Preserve negative title terms with a leading dash, e.g. 'product manager, software engineer, -senior'. If they want any role / all jobs, omit. Never merge many titles into one string unless the user supplied comma-separated roles. Expand shorthand (swe, pm, sre) when applicable. | |
| cursor | No | Pagination cursor from a previous search_jobs response to fetch the next page. | |
| remote | No | true: remote jobs only (any country unless country is set). Leave out place fields. location 'remote' does the same. | |
| applied | No | Filter by whether the user already applied. false: leave out jobs they applied to. true: only jobs they applied to. Omit to get every job; ones they applied to say applied: true. | |
| company | No | Employer slug(s): bare slug or comma-separated OR include (e.g. meta,google,apple). Prefix with '-' to exclude (e.g. -lucid-motors,-tesla). Mix allowed (meta,google,-amazon). Lowercase hyphenated. Mid-slug hyphens are part of the slug; only a leading '-' excludes. If include-only returns 0, retry without include slugs. | |
| country | No | ISO 3166-1 alpha-2 country filter (e.g. US, GB, DE). Returns jobs in that country or workplace_type remote. | |
| keywords | No | Only if the user named skills or stacks in this turn. Omit by default — do not pull from resume or profile. | |
| location | No | Display name of the place (e.g. 'San Francisco, CA'). When near_lat/near_lng are set this is only a label and is NOT used as a text filter. Otherwise a text filter on job location strings (partial match). For metro-area or 'near me' intent, prefer near_lat + near_lng + radius_km (50–65 km typical) so results are not tied to one city spelling. Use location only when you cannot geocode, or as a fallback. Avoid long 'City, Country' strings; use country for country filters. For multiple metros, prefer location_or. | |
| near_lat | No | Latitude for distance search. Use with near_lng. Typical source: browser geolocation or geocoded city. | |
| near_lng | No | Longitude for distance search. Required with near_lat. | |
| radius_km | No | Radius in kilometers around near_lat/near_lng. Default 50, max 500. | |
| exclude_ids | No | Comma-separated job IDs to exclude (e.g. postings already shown in the conversation). | |
| location_or | No | Comma-separated place substrings when the user names two or more metros at once (e.g. San Francisco,New York). The API returns jobs whose location text matches ANY term. Mutually exclusive with distance search (near_lat/near_lng). | |
| exclude_remote | No | Distance searches (near_lat/near_lng) return on-site and hybrid jobs in the radius. For remote jobs, search without near_lat/near_lng and set remote: true. | |
| employment_type | No | Type of employment contract. | |
| seniority_level | No | Omit unless the user explicitly asked for a band. Never infer from profile. Enum when set: | |
| visa_sponsorship | No | Filter by explicit visa sponsorship text in the posting (AI-extracted). Use 'yes' for jobs that sponsor visas (H-1B, etc.). Use 'no' only when the user wants roles that explicitly state no sponsorship. Omit when not relevant. | |
| posted_within_days | No | Days of posted-date lookback, at most 30. Omit → default 7. 0 → the full 30 days. 1 → today/last 24h. 7 → this week. Jobs older than 30 days are never returned. Never encode recency words in query. | |
| description_language | No | ISO 639-1 code for the language of the job posting body. Examples: en, es, de, fr, pt. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| jobs | No | Matching job listings. | |
| query | No | ||
| total | No | Total matches when provided by the API. | |
| cursor | No | Pagination cursor for the next page. | |
| search | No | Echo of search_jobs filters for the Job Cards widget. | |
| location | No | ||
| near_lat | No | ||
| near_lng | No |