Coding agent documentation index Fetch the complete documentation index at: https://docs.worklittle.com/docs-agent-manifest.json Use this file to discover all available pages before exploring further.

Tool chains

Call sequences for document tailoring, apply, ATS updates, market questions, and careers sites.

Chain 1: search to tailored document

search_jobs(query, filters, limit <= 20)
  > pick 1 to 3 results with the user or a ranking step
  > get_job_details(job_id)
  > get_job_keywords(job_id)
  > create_resume({ job_id, resume_text, job_context: keywords })
  > create_cover_letter({ job_id, ... })

Fetch details after ranking so you pay only for shortlisted roles. Feed keywords, not the full description, into document generation.

Chain 2: search to submitted application

search_jobs(...)
  > inspect can_apply on the chosen row
  ├─ Worklittle-hosted job
  │    GET /business/jobs/company/{company.slug}/{job_id}   # REST: read application_fields
  │    create_resume(...)             # optional, for resume_file
  │    confirm with the user
  │    submit_job_application({ job_id, name, email, answers, resume_file })
  └─ eligible external job
       confirm with the user
       apply_for_job({ job_id })
       check_application_status(session_id)  # session.id from the start; poll until completed

Both branches put the candidate's name in front of an employer. Confirm first. See Apply with AI.

Chain 3: ATS pipeline update

list_candidates({ posted_job_id })          # MCP filters: posted_job_id, bookmarked
  > get_candidate_profile(candidate_id)      # confirm identity before writing
  > update_candidates({ candidate_job_id, stage_key: "phone_screening", stage_label: "Phone screening" })
  > create_candidate_notes({ candidate_id, body })
  > create_candidate_interview({ candidate_id, ... })   # if scheduling

Stage lives on the candidate-job pair, so candidate_job_id is required. See ATS automation.

Chain 4: market question

get_market_overview()                 # free, global counts
  > answer counts, remote share, top hiring companies
  > only if the user asks to see roles: search_jobs(...)

GET /jobs/salary-average?title=...&country=US
  > report average with jobs_in_average

Do not answer aggregate questions by paginating search.

Chain 5: careers site request cycle

GET /business/jobs/company/:company?include=facets     # list, ETag cached
  > GET /business/jobs/company/:company/:slug                # application_fields + features
  > POST .../:slug/parse-resume                              # only if features.resume_autofill
  > POST .../:slug/submit-application
  > webhook job.published | job.updated | job.closed > revalidate cached pages

No API key is needed. See Embedded job board.