Skip to main content
Glama

UPFRONT tickets

find_ticket_groups
Read-onlyIdempotent

UPFRONT's own listings for one event that can be bought now, cheapest first. event_id is UPFRONT's event id (eventId in event results); this does not search by name or place.

quantity: the exact number of tickets needed together ("for two people" is 2). When set, only listings that sell that many as ONE group are returned; two separate listings can't be combined into one group. max_price/min_price: the per-ticket price in dollars, fees included. max_total_price: the budget for the whole group, in dollars, as the user stated it ("$200 for two" is 200). Needs quantity; UPFRONT works out the per-ticket limit from it. section: a section name or number ("112", "Floor", "Mezzanine"): only that section's listings. limit: how many listings to return (default 10, at most 25). eticket_only / instant_download_only: only listings with that delivery method. min_days_before_event / max_days_before_event: only listings released within that window before the event ("last-minute").

Returns:

  • totalListings, lowestAllInPrice, highestAllInPrice: across every listing matching the filters, not only those returned.

  • listings: the cheapest matches, each with section, row, allInPrice (per ticket, every fee included), totalAllInPrice (the group's price, when quantity is set), quantities (how many can be bought together from this listing), notes, standardSection, deliveryMethods and url.

  • moreListings: how many matched but weren't returned. Parking-only listings are left out, except on a parking event, where every listing is a parking pass.

notes (what the seller wrote, e.g. "Obstructed view") and standardSection (UPFRONT's name for the section, when matched) are the only view or location signals on a listing; there is no view-quality score. When they say nothing, no view information is available for that listing. Distance, height, cover and a picture of the view come from UPFRONT's section facts, at venues with an UPFRONT seating chart.

url is the link to buy exactly that listing (section, row and quantity) on UPFRONT; it is null only when the listing can't be bought.

{"error": "search_failed"} means the lookup failed after retries, not that no tickets exist. An empty listings list with no error means nothing matched the filters passed; it says nothing about why.

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": {
      "event_id": "<event_id>"
    },
    "name": "find_ticket_groups"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
sectionNo
event_idYes
quantityNo
max_priceNo
min_priceNo
eticket_onlyNo
max_total_priceNo
instant_download_onlyNo
max_days_before_eventNo
min_days_before_eventNo

Output Schema

NameRequiredDescriptionDefault
errorNo
listingsYes
quantityNo
moreListingsYes
totalListingsYes
lowestAllInPriceYes
highestAllInPriceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / max_price / anyOf
      Previous value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "pattern": "^(?!^[-+.]*$)[+-]?0*\\d*\\.?\\d*$",
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / max_total_price / anyOf
      Previous value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "pattern": "^(?!^[-+.]*$)[+-]?0*\\d*\\.?\\d*$",
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / min_price / anyOf
      Previous value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "pattern": "^(?!^[-+.]*$)[+-]?0*\\d*\\.?\\d*$",
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses that aggregate stats cover all matching listings rather than only returned ones, that parking listings are excluded except on parking events, and that url is null only when a listing is unbuyable. It also explains error semantics — {"error": "search_failed"} means the lookup failed after retries, not that no tickets exist, while an empty list means nothing matched — which is exactly the kind of failure-mode context an agent needs.

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?

Purpose is front-loaded in the first sentence, then parameters are presented as a scannable term-by-term list, followed by returns and caveats. It is long, and the Returns block partly restates fields that an output schema already covers, but the notes/standardSection and error paragraphs carry real information, so little is truly wasted.

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 an 11-parameter filtered search, the definition covers filtering semantics, group-quantity constraints, result ranking, aggregate-vs-returned counts, empty-result meaning, and error behavior. An agent has everything needed to call it correctly and interpret an empty or failed response.

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

Parameters5/5

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

With 0% schema description coverage across 11 parameters, the description carries the full burden and does so: it defines quantity as tickets sold as one group (two listings can't be combined), prices as per-ticket all-in dollars, max_total_price as a group budget that requires quantity, limit's default and 25 cap, and the day-window semantics for last-minute listings. This adds meaning the bare schema cannot supply.

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

Purpose4/5

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

The description opens with a specific verb+resource+scope: "UPFRONT's own listings for one event that can be bought now, cheapest first." It also rules out an adjacent capability ("this does not search by name or place"), which helps separate it from find_events, but it never distinguishes itself from listing-oriented siblings such as best_seats or compare_prices.

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?

It states an exclusion (no name/place search) and makes clear the tool requires an UPFRONT event_id already in hand, which implies usage after find_events. However, there is no explicit guidance on when to choose this over best_seats, compare_prices or section_info — the agent must infer the split among the ticket-listing siblings.

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.

Resources