JobApplication
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JOBAPP_HOME | No | Path to the JobApplication data folder (default: ~/JobApplication-data) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find_jobsC | Search the job sites now (or check on a search already running). |
| list_jobsC | List saved jobs (best match first by default). |
| job_detailsC | Everything about one job, including the description and keyword match. |
| build_resumeB | Build the tailored PDF resume for a job. variant: which resume to use if the user has several (saved for this job; 'auto' = pick automatically; leave empty to keep the current choice). |
| mark_jobC | Set status: new, interested, applied, interview, rejected, offer, ignored. |
| import_resume_prepareA | Start a resume import from a Word (.docx) or PDF file (docx_path = path to either): returns the prompt to follow. |
| import_resume_submit_texC | Check a LaTeX version of the imported resume against the source Word or PDF file. |
| cover_letter_prepareA | Start a tailored cover letter for a job (language 'en' or 'no'; default from coverletter/style.yaml): returns the prompt. Write only the letter body following it, then call cover_letter_submit. |
| cover_letter_submitB | Check a cover letter body (facts traceable to the resume/ad, length, banned phrases, keywords, language, one page). If it passes and accept_if_ok, makes the PDF + plain text in the output folder. |
| doctorC | Check the installation and settings; each problem has a fix hint. |
| update_config_filtersB | Change the job filters in config.yaml (only the fields you pass). Old file kept as config.yaml.bak. |
| open_dashboardA | Start the dashboard in the background (if needed) and open it in the browser. Returns its address. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose: the two-phase workflows (cover_letter_prepare/submit, import_resume_prepare/submit_tex) are explicitly named as pairs, and search/list/detail/status tools target separate concerns. Even closely related tools like import_resume_submit_tex vs build_resume are differentiated by their descriptions (import validation vs tailored PDF generation).
All names are consistently snake_case, which makes the set readable and predictable. However, verb position varies (verb_noun like list_jobs/build_resume vs noun_verb like cover_letter_prepare/import_resume_submit_tex), and singleton names like 'doctor' and 'job_details' don't follow the verb_noun pattern.
Twelve tools is well-scoped for a job-application assistant covering search, tracking, cover letters, resume import/build, config, and diagnostics. Each tool earns its place with no redundant or filler entries.
The surface covers the full workflow: find/detail/list jobs, mark status, tune filters, prepare/submit cover letters, import and build resumes, plus dashboard and diagnostics. Minor gaps exist (no delete/remove job, no explicit export or application-submission tool), but agents can work around these.