Skip to main content
Glama

Read a job analysis

get_vacancy_detail
Read-only

Get one vacancy fit analysis by id, with match percentage, verdict, key strengths, gaps, recommendations, and a skill-by-skill requirements comparison, vacancy_step — the next step on this vacancy, and app_url — the vacancy's page in ResumeQuick. Returns 'not_found' if the analysis does not exist or does not belong to the current user.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "input": "<input>"
    },
    "name": "get_vacancy_detail"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes

Output Schema

NameRequiredDescriptionDefault
idYes
urlNoLink to the original job posting, when known.
notesNoThe user's notes on this vacancy.
titleYesVacancy title (often includes company, e.g. 'Backend Engineer at Acme').
statusNoJob-tracker status: 'new' | 'applied' | 'interview' | 'offer' | 'rejected' | 'accepted'.new
app_urlYesLink to this vacancy's page in ResumeQuick, opened after signing in to this account; with a cover letter written it opens on the Cover Letter tab that keeps the letter.
companyNoCompany name, when known.
key_gapsNoGaps in the CANDIDATE relative to the posting. Never carries remarks about the posting text itself — those live in input_quality.
locationNoJob location, when known.
is_pinnedNoThe user pinned it to the top of their tracker; lists put pinned vacancies first.
step_pathNoPath on the ResumeQuick site where vacancy_step is done; null without one.
analyzed_atYesISO 8601 timestamp of when the vacancy was analyzed or, if never analyzed, added.
is_archivedNoArchived vacancies are hidden from the user's main list. Only an archived one can be deleted.
vacancy_stepNoThe step inside this vacancy, the same one its page shows: confirm_status (the posting requires a status the user has not stated; answer_vacancy_status records the answer), full_text (the analysis saw only part of the posting), tailor, cover_letter, apply, interview (it is at Interview), another (the analysis advises against it — the user's own next step from get_next_step is the one to take), or null (the analysis is not ready, or the case waits for the employer after an application).
input_qualityNoQuality of the posting text this analysis was based on. When truncated is true the score came from a fragment; analyze_tracked_vacancy re-runs it on the full text.
key_strengthsNoStrong points matching the vacancy.
status_historyNoJob-tracker status changes, oldest first; the history keeps the newest 100 events.
analysis_statusNo'completed' — analyzed; 'none' — tracked, never analyzed (match fields are null); 'processing' — an analysis is running right now; 'failed' — the last analysis failed. Lists only return 'completed' and 'none'; get_vacancy_detail returns every state.completed
chances_summaryNoShort prose verdict on chances (e.g. 'Strong fit, apply soon').
has_descriptionNoWhether the posting text is stored on this vacancy (the text itself is never returned). False means it cannot be analyzed until the text is added — analyze_tracked_vacancy takes it as 'description'.
recommendationsNoActionable steps to improve fit for this vacancy.
tailored_resumeNoThe tailored resume copy linked to this vacancy, if one exists (created by apply_vacancy_resume_suggestions with target='copy' or create_resume_version with vacancy_id).
verdict_summaryNoFinal verdict — 1–3 sentences explaining the recommendation.
has_cover_letterNoWhether a cover letter for this vacancy is already written and kept on its Cover Letter tab (the text itself is never returned). cover_letter_stale true means it predates the latest re-analysis.
match_percentageNo0–100, computed by the analysis; null for never-analyzed manual entries.
verdict_categoryNoOne of 'apply' | 'consider' | 'skip' | 'not_eligible' | 'confirm_status' | 'invalid', or null if not categorized. 'not_eligible' means a hard eligibility blocker applies — the user cannot take this role as posted no matter how high match_percentage is; eligibility_blockers carries the reason. 'confirm_status' means the posting requires a status the user has not stated, so the verdict is open until they answer the blocker's question.
prepared_by_quickNoTrue when Quick, the ResumeQuick agent, analysed this vacancy on its own from a radar find, without the user asking and without spending their limits; tailored_resume is then the copy it prepared. The vacancy page says so and lets the user remove it.
skills_comparisonNoSkill-by-skill comparison of resume vs. vacancy requirements: up to 10 key skills the posting names, not every requirement in it.
cover_letter_staleNoThe stored cover letter was written before the vacancy was analyzed again.
resume_suggestionsNoStructured resume-improvement suggestions for this vacancy, if generated. Empty until request_vacancy_resume_suggestions has run and completed. Their list order is the index space for apply_vacancy_resume_suggestions.
cover_letter_optionsNoThe options the stored cover letter was written with; null when there is no letter or it predates kept options. generate_cover_letter reuses each one it is not given.
eligibility_blockersNoWhy the user may not be able to take this role at all — work model, location, timezone, work authorization, relocation. Separate from skill fit and never reflected in match_percentage. Any 'hard' blocker means verdict_category is 'not_eligible', whatever the match score. A location blocker needs the user's location from career memory; without it there is none. Empty when nothing is known about the user or nothing conflicts.
applied_suggestion_indicesNoIndices (into resume_suggestions) that have already been applied to the resume.
declined_suggestion_indicesNoIndices (into resume_suggestions) of questions the person answered no to — the experience they ask about is not theirs.
unchanged_suggestion_indicesNoIndices (into resume_suggestions) whose last apply changed nothing: the resume states nothing they build on yet. Applying them again changes nothing until the resume gains what they need.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • changedOutput schema / $defs / EligibilityBlocker / properties / question / description
      Previous value: -"The yes-or-no question about the status; set on 'unconfirmed'."New value: +"The yes-or-no question about the status ('unconfirmed') or the place ('unverified')."
    • changedOutput schema / $defs / EligibilityBlocker / properties / severity / description
      Previous value: -"'hard' — the user cannot take this role as posted, and verdict_category is forced to 'not_eligible'; 'soft' — surmountable or marginal, the verdict stands; 'unconfirmed' — the posting requires a status the user has not stated, and verdict_category is 'confirm_status'."New value: +"'hard' — the user cannot take this role as posted, and verdict_category is forced to 'not_eligible'; 'soft' — surmountable or marginal, the verdict stands; 'unconfirmed' — the posting requires a status the user has not stated, and verdict_category is 'confirm_status'; 'unverified' — the posting requires a place (living there, on-site or relocating) and nothing is known of where the user lives, so the requirement is not checked and the verdict stands."
    • changedOutput schema / $defs / SkillMatch / properties / confidence / description
      Previous value: -"How well-supported actual_level is: 'high' | 'medium' | 'low'. Always 'low' when evidence is null. A low-confidence level is a guess, not a claim."New value: +"How well-supported actual_level is: 'high' | 'medium' | 'low'. Always 'low' when evidence is null; low with actual_level 'none' means the resume says nothing about this skill. A low-confidence level is a guess, not a claim."
    • changedOutput schema / $defs / SkillMatch / properties / evidence / description
      Previous value: -"The resume line that justifies actual_level. Null means the level is unsupported by the resume, not a fact about the user."New value: +"The resume line that justifies actual_level, possibly paraphrased or translated rather than quoted word for word. Null means the level is unsupported by the resume, not a fact about the user."
    • changedOutput schema / $defs / VacancyStatusChange / properties / at / description
      Previous value: -"When it moved, ISO 8601."New value: +"When it moved, ISO 8601: the day the user gave for it, else when it was recorded."
    • changedOutput schema / properties / eligibility_blockers / description
      Previous value: -"Why the user may not be able to take this role at all — work model, location, timezone, work authorization, relocation. Separate from skill fit and never reflected in match_percentage. Any 'hard' blocker means verdict_category is 'not_eligible', whatever the match score. Empty when nothing is known about the user or nothing conflicts."New value: +"Why the user may not be able to take this role at all — work model, location, timezone, work authorization, relocation. Separate from skill fit and never reflected in match_percentage. Any 'hard' blocker means verdict_category is 'not_eligible', whatever the match score. A location blocker needs the user's location from career memory; without it there is none. Empty when nothing is known about the user or nothing conflicts."
    • addedOutput schema / properties / prepared_by_quick
      Added value: +{
      +  "default": false,
      +  "description": "True when Quick, the ResumeQuick agent, analysed this vacancy on its own from a radar find, without the user asking and without spending their limits; tailored_resume is then the copy it prepared. The vacancy page says so and lets the user remove it.",
      +  "title": "Prepared By Quick",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / skills_comparison / description
      Previous value: -"Skill-by-skill comparison of resume vs. vacancy requirements (the structured requirements view)."New value: +"Skill-by-skill comparison of resume vs. vacancy requirements: up to 10 key skills the posting names, not every requirement in it."
    • changedOutput schema / properties / vacancy_step / description
      Previous value: -"The step inside this vacancy, the same one its page shows: confirm_status (the posting requires a status the user has not stated; answer_vacancy_status records the answer), tailor, cover_letter, apply, interview (it is at Interview), another (the analysis advises against it — the user's own next step from get_next_step is the one to take), or null (the analysis is not ready, or the case waits for the employer after an application)."New value: +"The step inside this vacancy, the same one its page shows: confirm_status (the posting requires a status the user has not stated; answer_vacancy_status records the answer), full_text (the analysis saw only part of the posting), tailor, cover_letter, apply, interview (it is at Interview), another (the analysis advises against it — the user's own next step from get_next_step is the one to take), or null (the analysis is not ready, or the case waits for the employer after an application)."
  2. Changed5 schema fields changed
    • addedOutput schema / $defs / EligibilityBlocker / properties / question
      Added value: +{
      +  "default": "",
      +  "description": "The yes-or-no question about the status; set on 'unconfirmed'.",
      +  "title": "Question",
      +  "type": "string"
      +}
    • changedOutput schema / $defs / EligibilityBlocker / properties / severity / description
      Previous value: -"'hard' — the user cannot take this role as posted, and verdict_category is forced to 'not_eligible'; 'soft' — surmountable or marginal, the verdict stands."New value: +"'hard' — the user cannot take this role as posted, and verdict_category is forced to 'not_eligible'; 'soft' — surmountable or marginal, the verdict stands; 'unconfirmed' — the posting requires a status the user has not stated, and verdict_category is 'confirm_status'."
    • changedOutput schema / properties / vacancy_step / anyOf
      Previous value: -[
      -  {
      -    "enum": [
      -      "tailor",
      -      "cover_letter",
      -      "apply",
      -      "interview",
      -      "another"
      -    ],
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "confirm_status",
      +      "full_text",
      +      "tailor",
      +      "cover_letter",
      +      "apply",
      +      "interview",
      +      "another"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedOutput schema / properties / vacancy_step / description
      Previous value: -"The step inside this vacancy, the same one its page shows: tailor, cover_letter, apply, interview (it is at Interview), another (the analysis advises against it — the user's own next step from get_next_step is the one to take), or null (the analysis is not ready, or the case waits for the employer after an application)."New value: +"The step inside this vacancy, the same one its page shows: confirm_status (the posting requires a status the user has not stated; answer_vacancy_status records the answer), tailor, cover_letter, apply, interview (it is at Interview), another (the analysis advises against it — the user's own next step from get_next_step is the one to take), or null (the analysis is not ready, or the case waits for the employer after an application)."
    • changedOutput schema / properties / verdict_category / description
      Previous value: -"One of 'apply' | 'consider' | 'skip' | 'not_eligible' | 'invalid', or null if not categorized. 'not_eligible' means a hard eligibility blocker applies — the user cannot take this role as posted no matter how high match_percentage is; eligibility_blockers carries the reason."New value: +"One of 'apply' | 'consider' | 'skip' | 'not_eligible' | 'confirm_status' | 'invalid', or null if not categorized. 'not_eligible' means a hard eligibility blocker applies — the user cannot take this role as posted no matter how high match_percentage is; eligibility_blockers carries the reason. 'confirm_status' means the posting requires a status the user has not stated, so the verdict is open until they answer the blocker's question."
  3. Changed1 schema field changed
    • addedOutput schema / properties / unchanged_suggestion_indices
      Added value: +{
      +  "description": "Indices (into resume_suggestions) whose last apply changed nothing: the resume states nothing they build on yet. Applying them again changes nothing until the resume gains what they need.",
      +  "items": {
      +    "type": "integer"
      +  },
      +  "title": "Unchanged Suggestion Indices",
      +  "type": "array"
      +}
  4. Changed2 schema fields changed
    • changedOutput schema / properties / analyzed_at / description
      Previous value: -"ISO 8601 timestamp."New value: +"ISO 8601 timestamp of when the vacancy was analyzed or, if never analyzed, added."
    • addedOutput schema / properties / is_pinned
      Added value: +{
      +  "default": false,
      +  "description": "The user pinned it to the top of their tracker; lists put pinned vacancies first.",
      +  "title": "Is Pinned",
      +  "type": "boolean"
      +}
  5. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the description earns credit for adding genuine context: the exact contents of the response, an authorization/ownership gate ('does not belong to the current user'), and the not_found failure mode. It stops short of pagination/size or latency notes, which is a minor gap for a single-record read.

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

Conciseness4/5

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

A single front-loaded sentence delivers the verb, the key, and the full return payload, with the not_found condition appended as a short second sentence. The inline clauses for vacancy_step and app_url are slightly clunky, but nothing is redundant.

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 need not spell out return shapes, and it still names the salient fields and the failure case. The only shortfall is that 0% schema coverage leaves the vacancy_id format and the ownership prerequisite implicit rather than stated.

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

Parameters3/5

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

Schema description coverage is 0%, so the description carries the burden. It does say the id identifies a vacancy analysis and comes from other vacancy tools, which is real guidance beyond the bare 'Id of the vacancy analysis' field text. However, it gives no id format or example, and the wrapper/input nesting is not explained, so coverage of the one parameter stays partial.

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?

States a specific verb and resource ('Get one vacancy fit analysis by id') and enumerates the payload an agent will receive (match percentage, verdict, strengths, gaps, recommendations, skill comparison, vacancy_step, app_url). This clearly distinguishes it from write-oriented siblings like analyze_vacancy or update_vacancy_status.

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?

The 'by id ... as returned by other vacancy tools' framing implies this is the follow-up read after a list or analyze call, and the ownership/not_found note implies a prerequisite. But it never explicitly says when to use this versus read_job_link, get_recent_vacancies, or get_next_step, so the agent must infer the routing.

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.