Skip to main content
Glama

List job matches

get_radar_matches
Read-only

List vacancies the user's job radar has found (automatic job search based on their resume), best match first. Each item carries title, company, location, match_grade (strong/possible/weak — the radar's rough fit; match_percentage is the same guess as a number and does not predict an analysis; both are null once the match is analyzed), the keywords behind it, the published salary when the board gave one, the applicant-tracking system behind the link, the level and employment type its title states (null when it states none), an opening snippet of the posting text and on_screen (whether the user has seen it in the app yet), analysis_id when this vacancy was already analyzed, with analysis_match_percentage once that analysis finished — then the only fit to quote (get_vacancy_detail reads it at no cost; analyze_radar_match analyzes one that has none). The stored snippet is all the posting text we hold. Optional status: 'new' (not yet reviewed) or 'saved' (liked) pick one half of the active list; 'deferred' reads the put-off-for-later pile and 'archived' the Skipped pile — everything the user skipped or put away, latest first, and where delete_radar_match takes its ids from. Omit for new plus saved. Narrow with min_match, is_remote, source, posted_after (ISO date), has_analysis, seniority and employment_type — the last two come from the title, so a posting whose title says nothing is dropped by them: a small result means most titles were silent, not that such jobs are rare. Order with sort='fresh' (newest posting first) instead of the default best-match. total says how many matched the filters; offset pages past the 30-item cap. Empty list is a normal result, and the usual one before the first start_radar_scan.

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_radar_matches"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputNo

Output Schema

NameRequiredDescriptionDefault
totalYesHow many matches passed the filters in total — not how many this page returned. Without filters it equals get_radar_status.active (the active list is read up to its first 300).
matchesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • changedInput schema / $defs / GetRadarMatchesInput / properties / min_match / description
      Previous value: -"Keep only matches at or above this percentage, 0..100."New value: +"Keep only matches at or above this percentage, 0..100 — the analysis's fit once it exists, the radar's guess before."
    • changedOutput schema / $defs / RadarMatchItem / properties / analysis_match_percentage / description
      Previous value: -"The finished analysis's own fit for this vacancy — the user's fit once it exists. Null until an analysis has completed."New value: +"The finished analysis's own fit for this vacancy — the user's fit once it exists, and the only fit this item carries then. Null until an analysis has completed."
    • addedOutput schema / $defs / RadarMatchItem / properties / match_grade / anyOf
      Added value: +[
      +  {
      +    "enum": [
      +      "strong",
      +      "possible",
      +      "weak"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / $defs / RadarMatchItem / properties / match_grade / default
      Added value: +null
    • changedOutput schema / $defs / RadarMatchItem / properties / match_grade / description
      Previous value: -"The radar's fit in words, the way the user sees it on the card: strong (80+), possible (50-79) or weak (below 50)."New value: +"The radar's fit in words, the way the user sees it on the card: strong (80+), possible (50-79) or weak (below 50). Null once analysis_match_percentage is set."
    • removedOutput schema / $defs / RadarMatchItem / properties / match_grade / enum
      Removed value: -[
      -  "strong",
      -  "possible",
      -  "weak"
      -]
    • removedOutput schema / $defs / RadarMatchItem / properties / match_grade / type
      Removed value: -"string"
    • addedOutput schema / $defs / RadarMatchItem / properties / match_percentage / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / $defs / RadarMatchItem / properties / match_percentage / default
      Added value: +null
    • changedOutput schema / $defs / RadarMatchItem / properties / match_percentage / description
      Previous value: -"Rough composite fit, not a skills-only score: title match, resume skills found in the posting, freshness and location fit. A fast guess, not an analysis — it does not predict the analysis score; match_grade is the same fit in words. matched_keywords shows what drove it."New value: +"Rough composite fit, not a skills-only score: title match, resume skills found in the posting, freshness and location fit. A fast guess, not an analysis — it does not predict the analysis score; match_grade is the same fit in words. matched_keywords shows what drove it. Null once analysis_match_percentage is set: the analysis replaces the guess, as on the user's card."
    • removedOutput schema / $defs / RadarMatchItem / properties / match_percentage / type
      Removed value: -"integer"
    • changedOutput schema / $defs / RadarMatchItem / required
      Previous value: -[
      -  "id",
      -  "title",
      -  "match_percentage",
      -  "match_grade",
      -  "source",
      -  "url",
      -  "status"
      -]New value: +[
      +  "id",
      +  "title",
      +  "source",
      +  "url",
      +  "status"
      +]
  2. Changed1 schema field changed
    • addedOutput schema / $defs / RadarMatchItem / properties / open_confirmed_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The last time the job board or its applicant-tracking system answered that the posting is open (the same nightly check, saved and put-off matches only). Null means openness is not confirmed, not that it is open: many boards never say, and new matches are not checked; first_seen_at is then the only date known.",
      +  "title": "Open Confirmed At"
      +}
  3. Changed2 schema fields changed
    • changedOutput schema / $defs / RadarMatchItem / properties / on_screen / description
      Previous value: -"True when the user has seen this match in the app: dealt into their radar deck, saved, put off or skipped, or analyzed (it is then in their vacancies). False while the user has not opened the radar since the scan found it; the next visit deals it on every plan."New value: +"True when the user has seen this match in the app: dealt into their radar deck, looked at in the radar feed, saved, put off or skipped, or analyzed (it is then in their vacancies). False while the user has not opened the radar since the scan found it; the next visit deals it on every plan."
    • changedOutput schema / $defs / RadarMatchItem / properties / status / enum
      Previous value: -[
      -  "new",
      -  "saved",
      -  "deferred",
      -  "archived",
      -  "skipped"
      -]New value: +[
      +  "new",
      +  "saved",
      +  "deferred",
      +  "archived",
      +  "skipped",
      +  "seen"
      +]
  4. Changed3 schema fields changed
    • removedOutput schema / $defs / RadarDeckItem
      Removed value: -{
      -  "properties": {
      -    "daily_left": {
      -      "description": "How many more the deck deals today, the next time the user opens the radar (0: today's are dealt).",
      -      "title": "Daily Left",
      -      "type": "integer"
      -    },
      -    "daily_limit": {
      -      "description": "How many new matches the free plan deals into the deck a UTC day.",
      -      "title": "Daily Limit",
      -      "type": "integer"
      -    },
      -    "next_deal_at": {
      -      "description": "When the next day's deal starts (UTC midnight), ISO 8601.",
      -      "title": "Next Deal At",
      -      "type": "string"
      -    },
      -    "pool_remaining": {
      -      "description": "Matches waiting in the pool behind the deck, not seen by the user yet.",
      -      "title": "Pool Remaining",
      -      "type": "integer"
      -    }
      -  },
      -  "required": [
      -    "daily_limit",
      -    "daily_left",
      -    "pool_remaining",
      -    "next_deal_at"
      -  ],
      -  "title": "RadarDeckItem",
      -  "type": "object"
      -}
    • changedOutput schema / $defs / RadarMatchItem / properties / on_screen / description
      Previous value: -"True when the user can see this match in the app: dealt into their radar deck, saved, put off or skipped, or analyzed (it is then in their vacancies). False while it waits in the pool behind the deck — the user has not seen it and will not find it on the radar screen yet."New value: +"True when the user has seen this match in the app: dealt into their radar deck, saved, put off or skipped, or analyzed (it is then in their vacancies). False while the user has not opened the radar since the scan found it; the next visit deals it on every plan."
    • removedOutput schema / properties / deck
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "$ref": "#/$defs/RadarDeckItem"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "The free plan's daily deck: the radar screen deals a few new matches a day out of the pool. Null on a paid plan, whose deck is not limited by day, and on the deferred and archived piles."
      -}
  5. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare a safe read; the description adds the operational traits that matter: a 30-item cap with offset paging, a total count of filter matches, archived ordering as latest-first, and that match_grade/match_percentage are the radar's rough guess that becomes null once analyzed. The filter caveats — undated postings dropped by posted_after, silent titles dropped by seniority/employment_type — prevent the agent from misreading a small result set as scarcity.

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 and most clauses do work, but it is a single dense block with nested em-dash parentheticals that is hard to scan. The long enumeration of returned fields (title, company, location, match_grade, salary, ATS, snippet, on_screen, analysis_id) is largely redundant given an output schema exists.

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 tool with twelve filters, paging, four status piles and analysis-linked fields, nothing an agent needs to call it correctly is missing — defaults, ordering, empty-result meaning, filter null-dropping behavior and the cost-free path to the analyzed fit are all covered. Return values are also backed by an output schema, so the description is more than complete.

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?

With the top-level input parameter carrying no schema description, the description carries the burden and largely does: it defines all four status piles, min_match as analysis fit once it exists versus the radar guess before, has_analysis, source, is_remote, posted_after semantics, and the 30-item paging cap. It omits limit's default of 10 and 1..30 range, and several filter explanations closely restate the nested schema text rather than adding to it.

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 — list the vacancies the user's job radar found, best match first — and immediately qualifies the source as an automatic resume-based search. It also names the related siblings (get_vacancy_detail, analyze_radar_match, delete_radar_match, start_radar_scan) in their exact roles, so an agent can place this tool precisely.

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

Usage Guidelines4/5

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

Gives concrete routing rules: omit status for new+saved, use status='archived' for Skipped and note that is where delete_radar_match takes its ids, use sort='fresh' when applying in volume, and treat an empty list as normal before start_radar_scan. It does not explicitly contrast against other listing siblings (e.g. get_recent_vacancies, list_offers), which keeps it from a 5.

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.