Skip to main content
Glama

Ticker: Live Event Ticket Market

by com.findticker
OverviewDiscussionsAdmin

List Matches

list_matches
Read-only

Lists the events that entered the caller's Views, newest first, with delivery_status; with view_id it adds a summary of the View. With match_id it shows one Match in full: the event and its numbers frozen when it entered the View. Read delivery_status, never a timestamp, for whether an email went out. Replaces get_match.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo
limitNo
sinceNoISO 8601 timestamp; only matches at/after this. Default: 7 days ago.
view_idNo
event_idNo
match_idNoThe match id (from list_matches' match_id field).
delivery_statusNoDELIVERY TRUTH: read `delivery_status`, never infer delivery from a timestamp: 'sent' = an alert email actually carried this Match; 'not_sent' = terminally dropped and never sent (see `delivery_reason`, e.g. muted_view, locked_view, email_digests_off (the owner turned alert emails off), view_disabled); 'pending' = not processed yet, may still be sent; 'not_applicable' = was never eligible for an alert email (a baseline Match, or a View that delivers only to alert destinations). `notified_at` is non-null ONLY when delivery_status is 'sent'; `consumed_at` is when the Match was claimed whatever the outcome. NEVER report a Match as delivered unless delivery_status is 'sent'. Only Matches in this delivery state. Use 'sent' for "which alert emails actually went out" and 'not_sent' for "what was dropped, and why"; do NOT infer either from a timestamp. Note: the 'not_applicable' filter matches baseline Matches only; destination-only Views are labeled not_applicable on the row but are not selected by this filter.
include_snapshotNoInline the full frozen snapshot (event + event_analytics + performer_analytics) on every row. Heavy: a page can exceed the tool result token cap. Prefer the compact default + get_match for drill-down.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / delivery_status / description
      Previous value: -"Only Matches in this delivery state. Use 'sent' for \"which alert emails actually went out\" and 'not_sent' for \"what was dropped, and why\"; do NOT infer either from a timestamp. Note: the 'not_applicable' filter matches baseline Matches only; destination-only Views are labeled not_applicable on the row but are not selected by this filter."New value: +"DELIVERY TRUTH: read `delivery_status`, never infer delivery from a timestamp: 'sent' = an alert email actually carried this Match; 'not_sent' = terminally dropped and never sent (see `delivery_reason`, e.g. muted_view, locked_view, email_digests_off (the owner turned alert emails off), view_disabled); 'pending' = not processed yet, may still be sent; 'not_applicable' = was never eligible for an alert email (a baseline Match, or a View that delivers only to alert destinations). `notified_at` is non-null ONLY when delivery_status is 'sent'; `consumed_at` is when the Match was claimed whatever the outcome. NEVER report a Match as delivered unless delivery_status is 'sent'. Only Matches in this delivery state. Use 'sent' for \"which alert emails actually went out\" and 'not_sent' for \"what was dropped, and why\"; do NOT infer either from a timestamp. Note: the 'not_applicable' filter matches baseline Matches only; destination-only Views are labeled not_applicable on the row but are not selected by this filter."
    • removedInput schema / properties / include_snapshot / default
      Removed value: -false
    • removedInput schema / properties / limit / default
      Removed value: -20
    • addedInput schema / properties / match_id
      Added value: +{
+  "description": "The match id (from list_matches' match_id field).",
+  "format": "uuid",
+  "type": "string"
+}
    • removedInput schema / properties / page / default
      Removed value: -1
  2. Changed2 schema fields changed
    • removedInput schema / properties / limit / maximum
      Removed value: -100
    • changedInput schema / properties / since / description
      Previous value: -"ISO 8601 timestamp; only matches at/after this."New value: +"ISO 8601 timestamp; only matches at/after this. Default: 7 days ago."
  3. Changed2 schema fields changed
    • changedInput schema / properties / delivery_status / description
      Previous value: -"Only Matches in this delivery state. Use 'sent' for \"which alert emails actually went out\" and 'not_sent' for \"what was dropped, and why\" — do NOT infer either from a timestamp. Note: the 'not_applicable' filter matches baseline Matches only; destination-only Views are labelled not_applicable on the row but are not selected by this filter."New value: +"Only Matches in this delivery state. Use 'sent' for \"which alert emails actually went out\" and 'not_sent' for \"what was dropped, and why\"; do NOT infer either from a timestamp. Note: the 'not_applicable' filter matches baseline Matches only; destination-only Views are labeled not_applicable on the row but are not selected by this filter."
    • changedInput schema / properties / include_snapshot / description
      Previous value: -"Inline the full frozen snapshot (event + event_analytics + performer_analytics) on every row. Heavy — a page can exceed the tool result token cap. Prefer the compact default + get_match for drill-down."New value: +"Inline the full frozen snapshot (event + event_analytics + performer_analytics) on every row. Heavy: a page can exceed the tool result token cap. Prefer the compact default + get_match for drill-down."
  4. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safe read profile (readOnlyHint/destructiveHint/openWorldHint), yet the description adds real behavior: newest-first ordering, that match_id returns the event and its numbers frozen at View-entry time, and the delivery-status truth rule. It does not mention pagination limits or the heavy-payload risk of snapshots, which live only in the schema.

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-loads the default behavior, then the two modifier modes, then the delivery-status rule, ending with the replacement note. Four dense sentences with no filler; the 'Replaces get_match' clause is terse but useful rather than wasteful.

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?

No output schema exists, but the description covers the primary mode semantics, ordering, and the critical delivery-status interpretation, so an agent can call it correctly. The remaining gaps (event_id's effect, pagination behavior) are minor for the common paths.

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?

At 50% schema coverage the description carries part of the load: it explains what view_id and match_id change about the response, which the schema only types. The richest parameter semantics (delivery_status enum meanings, include_snapshot heaviness) sit in the schema itself, and event_id/page/limit remain unexplained in both.

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?

Specific verb+resource ('Lists the events that entered the caller's Views') with ordering (newest first) and a clear disambiguation of its three modes keyed by view_id and match_id. It also names the sibling it replaces (get_match), so an agent can route without opening either schema.

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 explicit conditions for each mode ('with view_id it adds...', 'With match_id it shows one Match in full') and a firm usage rule ('Read delivery_status, never a timestamp'), plus the replacement relationship to get_match. It stops short of stating when NOT to use it or naming a live alternative for the single-match case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ticker: Live Event Ticket Market toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources