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.

Structured extraction

Use job keywords and structured detail fields instead of raw description text.

Three tiers of job text

| Tier | Source | Contains | Use for |
| --- | --- | --- | --- |
| **List row** | `GET /jobs`, `search_jobs` | Title, company, location, flags, short summary | Ranking, display, filtering |
| **Detail** | `GET /jobs/:id`, `get_job_details` | Responsibilities, qualifications, structured fields, salary hints | Explaining a role |
| **Keywords** | `get_job_keywords` | Skills and technologies, prose removed | Resume and cover letter tailoring, skill overlap |

Use the lowest tier that answers the question. Pass keywords as job_context on create_resume and create_cover_letter. Full descriptions degrade output.

Structured fields over parsing

| Want | Field |
| --- | --- |
| Can this be automated? | `can_apply` |
| Is this role still open? | `closed_at` |
| Where is it? | Geocoded location fields, not the title string |
| Seniority | `seniority_level` filter |
| What does it pay? | Salary fields on detail, or `/jobs/salary-average` for a query |
| What does the form ask? | `application_fields` on the board job detail (`GET /business/jobs/company/:company/:idOrSlug`) |
| Can I autofill a resume? | `features.resume_autofill` |

Worklittle already ran enrichment for salary, location, experience level, and similar attributes. Re-deriving them from free text in your own code gives a worse answer and drifts from what the filters match on.

Thin listings

Some sources return a title and a one-line snippet until enrichment runs.

A list row summary is a snippet. Do not present it as the description. If get_job_details returns an empty or near-empty body, say the description is not available. Do not infer requirements from the title. GET /jobs/:id returns raw text and cached AI for free. ?summary=true generates first-time AI text: 100 free per org per UTC day, then token rates. On public boards, description_sections and description_sections_meta are never an empty unusable body.