Skip to main content
Glama

Analyze a tracked job

analyze_tracked_vacancy

Analyze a vacancy already in the user's tracker (by vacancy_id) against their active resume, in place — no duplicate is created. It covers a vacancy never analyzed (analysis_status 'none'), one whose analysis failed, and a re-run (e.g. the first read a truncated posting). Consumes one vacancy analysis from the user's quota; while the posting text, the resume and what the user told are as they were, the last analysis stands and nothing is spent (status 'completed', reused true). Runs asynchronously: get_vacancy_detail(vacancy_id) shows the result once done, usually within 10 seconds. Returns 'description_required' when the vacancy has no posting text (pass the user's pasted text as 'description'), 'posting_too_short' when a never-analyzed vacancy holds only a job board's teaser of under 400 characters (nothing analyzed or spent; the full posting text passed as 'description' lifts it), 'already_processing' when an analysis of it is already running (nothing spent), 'limit_exceeded' naming the day it frees up when the quota is gone, and 'not_found' if the vacancy 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": "analyze_tracked_vacancy"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes

Output Schema

NameRequiredDescriptionDefault
reusedNoTrue: the posting text, the resume and what the user told are as they were, nothing was spent.
statusNo'completed' — nothing changed since the last analysis, and that analysis stands as it is.processing
task_idYesBackground task id (informational; get_vacancy_detail shows progress).
analysis_idYesThe same vacancy id — the analysis runs on this row, not a new one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / properties / reused
      Added value: +{
      +  "default": false,
      +  "description": "True: the posting text, the resume and what the user told are as they were, nothing was spent.",
      +  "title": "Reused",
      +  "type": "boolean"
      +}
    • removedOutput schema / properties / status / const
      Removed value: -"processing"
    • addedOutput schema / properties / status / description
      Added value: +"'completed' — nothing changed since the last analysis, and that analysis stands as it is."
    • addedOutput schema / properties / status / enum
      Added value: +[
      +  "processing",
      +  "completed"
      +]
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

With annotations declaring non-read-only, non-destructive, non-idempotent, the description adds substantial context the annotations cannot: quota consumption, the reuse/caching rule ('the last analysis stands and nothing is spent'), asynchronous execution with an expected ~10 second turnaround, and a full error-code catalogue. It stops short of describing authorization requirements or exactly what 'reused true' implies for the response shape, but this is well beyond the annotation baseline.

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?

Nothing is filler — purpose leads, then eligibility cases, then cost/reuse semantics, and finally the return codes. The drawback is density: it is a single long paragraph whose later clauses (quota reuse, five status codes) are harder to scan than a short list would be.

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

Completeness5/5

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

For a quota-consuming, async mutation tool it covers everything a caller needs: preconditions, cost behavior, polling path, and every failure return with its remedy. With an output schema present, it correctly does not waste space on success-shape details.

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?

Adds real meaning beyond the schema by binding each parameter to a situation: vacancy_id must come from the tracker (get_vacancy_detail id), and description is the condition-triggered escape hatch for 'description_required' and 'posting_too_short', including that it overwrites any teaser before analysis. Schema descriptions are present but the description supplies the decision logic for when each is required.

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 ('Analyze a vacancy already in the user's tracker') plus the key scoping constraint 'in place — no duplicate is created', which implicitly separates it from analyze_vacancy and analyze_radar_match. An agent can tell from the first clause that it must already hold a vacancy_id, unlike sibling analyze tools that work off other inputs.

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

Usage Guidelines5/5

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

Explicitly enumerates the three situations this covers: never analyzed (analysis_status 'none'), a previously failed analysis, and a re-run such as a truncated first read. It also routes the agent onward ('get_vacancy_detail(vacancy_id) shows the result once done') and points to analyze_radar_match's needs_full_posting as a trigger for the description parameter.

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.