Skip to main content
Glama

Compare all-in prices

compare_prices
Read-onlyIdempotent

One event's all-in prices on every site in one answer: UPFRONT's own listings and the other marketplaces (StubHub, SeatGeek, Vivid Seats, TickPick, Gametime, AXS, Ticketmaster), cheapest first. Matches requests like "cheapest 2 seats together for Saturday's game under $500 total" or "who has it cheaper?". event_id is UPFRONT's event id (eventId in event results).

quantity: how many tickets are needed together. Only listings that sell exactly that many as one group count, and totalAllInPrice is the whole group's price. max_price: the most per ticket, fees included, in dollars. max_total_price: the budget for the whole group, as the user stated it (needs quantity); UPFRONT works out the per-ticket limit. section: a section name or number ("112", "Floor"): only that section. limit: how many picks to return (default 5, at most 10).

Returns:

  • event: name, venue, city, startsAt and url (the event's page).

  • sites: one per site, cheapest first: site ("UPFRONT" for ours), checked, checkedAt, listings (how many match there) and lowestAllInPrice. checked "ok" means the site was read; "incomplete" means only some listings came back; "failed" means it couldn't be read, which is not the same as having nothing. A site missing from sites wasn't matched to this event, which is not the same as sold out there.

  • listings: the cheapest matching picks across every site: site, section, row, allInPrice (per ticket, that site's own price with its fees), totalAllInPrice (with quantity), quantities, notes and url, the link to buy exactly that listing on that site. feesIncluded false (rare) means that site gave no fees-in price.

  • moreListings: how many matched but weren't returned.

Other sites' prices are as of checkedAt and may have changed since. otherSites says where they came from: "saved" is UPFRONT's last check of each site, which can be hours or a few days old; "none" means no recent check, and event.url compares every site live. All prices are all-in totals. unavailable means other sites' prices aren't offered in this assistant right now; UPFRONT's own listings still stand. notShown lists sites whose prices aren't offered here, which is not the same as not found or sold out. error "search_failed" (on a site or the answer) means that lookup failed, not that nothing is on sale; "event_not_found" means no event has that id.

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": "compare_prices"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
sectionNo
event_idYes
quantityNo
max_priceNo
max_total_priceNo

Output Schema

NameRequiredDescriptionDefault
errorNo
eventNo
sitesYes
listingsYes
notShownNo
quantityNo
otherSitesNo
unavailableNo
moreListingsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 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"
      +  }
      +]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent annotations by disclosing staleness semantics ('saved' can be hours or days old vs 'none' meaning no recent check), the three-state site status where 'incomplete' and 'failed' are explicitly not 'nothing available', and that a site missing from `sites` means unmatched rather than sold out. The `unavailable`/`notShown`/`search_failed`/`event_not_found` distinctions are exactly the kind of false-negative protection an agent needs before reporting 'no tickets'.

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?

Front-loaded with the one-sentence purpose plus example phrasings, then a clean parameter block and a structured Returns block; the parameter paragraphs each earn their place. It runs long and duplicates a fair amount of the return shape that an output schema already covers, which keeps it from a 5, but there is little genuinely redundant prose.

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 six-parameter, open-world aggregator with fallible upstream sites, the definition covers the input semantics, the freshness caveat, the partial-failure states, and the distinction between 'not offered' and 'not found'. Nothing an agent needs in order to call it correctly or interpret a thin result is missing.

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?

Schema description coverage is 0%, so the description carries the full burden and does: event_id is tied to eventId in event results, quantity is defined as a group constraint with totalAllInPrice scoped to the whole group, max_price is bounded to per-ticket-with-fees, max_total_price is defined as the user's stated budget from which UPFRONT derives the per-ticket limit, and limit's default of 5 with a ceiling of 10 is stated. That is meaning well beyond the bare types in the schema.

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?

Opens with a specific verb and resource: an event's all-in prices across every site, naming both UPFRONT's own listings and the named marketplaces, sorted cheapest first. An agent can immediately tell this apart from siblings like best_seats or section_info, which scope to seating rather than cross-site price comparison.

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 trigger phrases ('cheapest 2 seats together for Saturday's game under $500 total', 'who has it cheaper?') that map directly onto the max_total_price and quantity parameters, which is strong usage framing. It does not, however, explicitly exclude or point to sibling tools (e.g. best_seats) when the user wants seat-quality advice rather than price, and the only alternative offered is the generic event.url for live checks.

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