Skip to main content
Glama

Get the next step

get_next_step
Read-only

Get the user's one next step in the job search — the same step the ResumeQuick home screen shows — with the reason from their data and, when the step is about a vacancy, that vacancy and the step inside it (vacancy.vacancy_step), and app_url — the screen in ResumeQuick where the step is done. After an application the vacancy leaves the ladder and has no step until the employer answers; the ladder has no follow-up step for it, and the step moves to new radar matches or another analysed vacancy. Args: {}.

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": "get_next_step"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
stepYesThe user's one next step, the same one the home screen shows: paused (the user paused the search until a date; there is no step until it ends or they resume it), no_resume (the account has no resume yet; making the first one opens the fit of jobs the radar finds by the named role), resume (the active resume lists no work experience and the user has never edited it; adding a job or any edit by the user clears it), radar (the job radar is off, nothing is analysed yet, or it has new matches), interview_prep (a vacancy moved to Interview within 14 days), vacancy (an analysis from the last 72 hours, not applied to), saved (saved radar matches not analysed), revisit (the best-scored analysis of the last 14 days not applied to), cycle (none of these).
matchNoThe radar match the step is about. On the saved step: the strongest one saved, not analysed and not known to be closed — the same one the end of the radar deck offers. On the radar step with new matches: the strongest one the user has not judged yet, which save_radar_match keeps. Null otherwise.
radarYesoff (the automatic daily search is off — get_radar_status.auto_search_enabled is false; matches already found stay), searching (on, with no new or saved match in the working list), matches (on, with at least one).
reasonYesWhy this step, from the user's data.
app_urlNoFull link to step_path on the ResumeQuick site, opened after signing in to this account; null when paused.
vacancyNoThe vacancy the step is about (vacancy, revisit, interview_prep); null otherwise.
step_pathNoPath on the ResumeQuick site where the step is done, the same screen the home card opens; null when paused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / $defs / NextStepVacancy / properties / prepared_by_quick / description
      Previous value: -"True when Quick, the ResumeQuick agent, analysed this vacancy on its own and the user has not opened it yet: it prepared resume suggestions for it (suggested; nothing is applied until the user applies them), found the resume fits as it is (fits_as_is), or, before 13.11.2026, tailored a copy. step_path then opens that work: the Tailoring tab, or the analysis."New value: +"True when Quick, the ResumeQuick agent, analysed this vacancy on its own and the user has not opened it yet: it prepared resume suggestions for it (suggested; nothing is applied until the user applies them), or found the resume fits as it is (fits_as_is). step_path then opens that work: the Tailoring tab, or the analysis."
  2. Changed2 schema fields changed
    • changedOutput schema / $defs / NextStepVacancy / properties / prepared_by_quick / description
      Previous value: -"True when Quick, the ResumeQuick agent, analysed this vacancy on its own and the user has not opened it yet: it either tailored a copy of the resume for it or found the resume fits as it is (fits_as_is). step_path then opens that work: the Tailoring tab with the copy, or the analysis."New value: +"True when Quick, the ResumeQuick agent, analysed this vacancy on its own and the user has not opened it yet: it prepared resume suggestions for it (suggested; nothing is applied until the user applies them), found the resume fits as it is (fits_as_is), or, before 13.11.2026, tailored a copy. step_path then opens that work: the Tailoring tab, or the analysis."
    • addedOutput schema / $defs / NextStepVacancy / properties / suggested
      Added value: +{
      +  "default": false,
      +  "description": "With prepared_by_quick: Quick prepared suggestions; the user applies them from the Tailoring tab.",
      +  "title": "Suggested",
      +  "type": "boolean"
      +}
  3. Changed5 schema fields changed
    • addedOutput schema / $defs / NextStepVacancy / properties / fits_as_is
      Added value: +{
      +  "default": false,
      +  "description": "With prepared_by_quick: the resume already fits the vacancy, so Quick made no copy.",
      +  "title": "Fits As Is",
      +  "type": "boolean"
      +}
    • addedOutput schema / $defs / NextStepVacancy / properties / prepared_by_quick
      Added value: +{
      +  "default": false,
      +  "description": "True when Quick, the ResumeQuick agent, analysed this vacancy on its own and the user has not opened it yet: it either tailored a copy of the resume for it or found the resume fits as it is (fits_as_is). step_path then opens that work: the Tailoring tab with the copy, or the analysis.",
      +  "title": "Prepared By Quick",
      +  "type": "boolean"
      +}
    • changedOutput schema / $defs / NextStepVacancy / properties / vacancy_step / description
      Previous value: -"The step inside this vacancy: tailor (no tailoring suggestions yet), cover_letter (suggestions exist, no cover letter), apply (suggestions and letter ready, not applied), interview (the vacancy is in Interview status). null when the vacancy has nothing left to prepare."New value: +"The step inside this vacancy: confirm_status (the posting requires a status the user has not stated), full_text (the analysis saw only part of the posting), tailor (no tailoring suggestions yet), cover_letter (suggestions exist, no cover letter), apply (ready to apply: suggestions and letter are done, or the user has tailored and written letters before), interview (the vacancy is in Interview status). null when the vacancy has nothing left to prepare. The same values as get_vacancy_detail.vacancy_step."
    • changedOutput schema / properties / step / description
      Previous value: -"The user's one next step, the same one the home screen shows: paused (the user paused the search until a date; there is no step until it ends or they resume it), resume (the active resume lists no work experience and the user has never edited it; adding a job or any edit by the user clears it), radar (the job radar is off, nothing is analysed yet, or it has new matches), interview_prep (a vacancy moved to Interview within 14 days), vacancy (an analysis from the last 72 hours, not applied to), saved (saved radar matches not analysed), revisit (the best-scored analysis of the last 14 days not applied to), cycle (none of these)."New value: +"The user's one next step, the same one the home screen shows: paused (the user paused the search until a date; there is no step until it ends or they resume it), no_resume (the account has no resume yet; making the first one opens the fit of jobs the radar finds by the named role), resume (the active resume lists no work experience and the user has never edited it; adding a job or any edit by the user clears it), radar (the job radar is off, nothing is analysed yet, or it has new matches), interview_prep (a vacancy moved to Interview within 14 days), vacancy (an analysis from the last 72 hours, not applied to), saved (saved radar matches not analysed), revisit (the best-scored analysis of the last 14 days not applied to), cycle (none of these)."
    • changedOutput schema / properties / step / enum
      Previous value: -[
      -  "paused",
      -  "resume",
      -  "radar",
      -  "interview_prep",
      -  "vacancy",
      -  "saved",
      -  "revisit",
      -  "cycle"
      -]New value: +[
      +  "paused",
      +  "no_resume",
      +  "resume",
      +  "radar",
      +  "interview_prep",
      +  "vacancy",
      +  "saved",
      +  "revisit",
      +  "cycle"
      +]
  4. Changed1 schema field changed
    • changedOutput schema / $defs / NextStepVacancy / properties / vacancy_step / anyOf
      Previous value: -[
      -  {
      -    "enum": [
      -      "tailor",
      -      "cover_letter",
      -      "apply",
      -      "interview"
      -    ],
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "confirm_status",
      +      "full_text",
      +      "tailor",
      +      "cover_letter",
      +      "apply",
      +      "interview"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  5. Changed5 schema fields changed
    • addedOutput schema / properties / app_url
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Full link to step_path on the ResumeQuick site, opened after signing in to this account; null when paused.",
      +  "title": "App Url"
      +}
    • changedOutput schema / properties / radar / description
      Previous value: -"off (the automatic daily search is off — get_radar_status.auto_search_enabled is false; matches already found stay), searching (on, radar_matches is 0), matches (on, radar_matches above 0)."New value: +"off (the automatic daily search is off — get_radar_status.auto_search_enabled is false; matches already found stay), searching (on, with no new or saved match in the working list), matches (on, with at least one)."
    • removedOutput schema / properties / radar_matches
      Removed value: -{
      -  "description": "Radar matches still in the working list: new ones, whether already shown or still waiting in the pool, and saved ones; skipped, deferred and archived ones are not counted. An input to the step: the job the step is about is in match and reason, which state no count.",
      -  "title": "Radar Matches",
      -  "type": "integer"
      -}
    • removedOutput schema / properties / saved_to_analyze
      Removed value: -{
      -  "description": "Saved radar matches with no analysis. An input to the step: the one saved job the step names is in match and reason, which state no count.",
      -  "title": "Saved To Analyze",
      -  "type": "integer"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "step",
      -  "reason",
      -  "radar",
      -  "radar_matches",
      -  "saved_to_analyze"
      -]New value: +[
      +  "step",
      +  "reason",
      +  "radar"
      +]
  6. Changed2 schema fields changed
    • changedOutput schema / properties / radar_matches / description
      Previous value: -"Radar matches still in the working list: new ones, whether already shown or still waiting in the pool, and saved ones; skipped, deferred and archived ones are not counted."New value: +"Radar matches still in the working list: new ones, whether already shown or still waiting in the pool, and saved ones; skipped, deferred and archived ones are not counted. An input to the step: the job the step is about is in match and reason, which state no count."
    • changedOutput schema / properties / saved_to_analyze / description
      Previous value: -"Saved radar matches with no analysis."New value: +"Saved radar matches with no analysis. An input to the step: the one saved job the step names is in match and reason, which state no count."
  7. First observed

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description's job is to add domain behavior — and it does: it explains the 'ladder' model, that a vacancy leaves the ladder after an application and has no step until the employer answers, and that the returned app_url is the screen where the step is performed. It stops short of stating any auth, caching, or freshness guarantees, but the state-machine explanation is genuinely useful context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, which is good, but the first sentence is a long chain of em-dash clauses that takes effort to parse, and the trailing 'Args: {}' is pure noise against an already-empty schema. The post-application edge case earns its place; the empty-args fragment does not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't document the return shape in full, yet it still clarifies the tricky nested field (vacancy.vacancy_step) and the meaning of app_url. Combined with the post-application state explanation, an agent has enough to call this zero-argument tool correctly and interpret the result; only explicit alternatives for other needs are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, which is the baseline-4 case, and the schema already confirms an empty object. The trailing 'Args: {}' adds nothing beyond the schema but does not mislead; there are simply no parameters whose meaning could be elaborated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — retrieving the user's single next step in the job search — and pins it to a concrete referent ('the same step the ResumeQuick home screen shows'). It also enumerates what comes back (reason from data, the vacancy and vacancy.vacancy_step when relevant, app_url), so an agent can distinguish this singular 'next step' tool from list-style siblings like get_radar_matches or get_recent_vacancies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by the 'home screen' analogy, which signals this is the default orientation call, and the post-application note explains a state where the step shifts to radar matches or another analysed vacancy. However, no sibling is named as an alternative and there are no explicit when-not-to-use conditions, so routing still requires inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.