Skip to main content
Glama
Sign In

CI Treasure Hunt

by com.citreasurehunt
OverviewDiscussionsAdmin

Search events

search_events
Read-onlyIdempotent

Find Contact Improvisation events worldwide: festivals, workshops, intensives, retreats, long jams, residencies, jams and classes. Upcoming by default; a past 'from' date also searches ended events. Use for questions like 'CI festivals in Germany this summer', 'workshops with ' or 'when was X last year'. Filter by country, city, dates, type, practice or free text. Returns up to 20 events sorted by start date, each with id and citreasurehunt.com URL, plus the total match count. Call get_event for prices, teachers and the full description.

Input Schema

NameRequiredDescriptionDefault
toNoWindow end: the latest start date, YYYY-MM-DD.
cityNoCity name, e.g. Berlin.
fromNoWindow start, YYYY-MM-DD. Default today. Includes events still running on or after this date; a past date also returns ended events.
typeNoEvent type.
limitNoMaximum results, 1 to 20. Default 10.
queryNoFree text matched against title, description and place, e.g. a teacher's name or 'silent'.
countryNoCountry as ISO code ("PT") or English name ("Portugal").
featuresNoOnly events offering all of these, e.g. ["residential", "meals"] or ["sliding_scale"].
practiceNoPractice tag, e.g. "contact_improvisation" (default), "conscious_dance", "axis_syllabus", or "any" for all practices.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / features
      Added value: +{
+  "description": "Only events offering all of these, e.g. [\"residential\", \"meals\"] or [\"sliding_scale\"].",
+  "items": {
+    "enum": [
+      "residential",
+      "meals",
+      "sauna",
+      "swimming_pool",
+      "nature",
+      "by_the_sea",
+      "mountains",
+      "jams",
+      "silent_jam",
+      "live_music",
+      "self_organized",
+      "outdoor_dancing",
+      "hiking",
+      "site_specific",
+      "labs",
+      "underscore",
+      "contemplative_dance",
+      "ensemble_thinking",
+      "performance",
+      "talks",
+      "film_screenings",
+      "meditation",
+      "water_practice",
+      "silence",
+      "teacher_training",
+      "sliding_scale",
+      "work_exchange",
+      "scholarships",
+      "family_friendly",
+      "childcare",
+      "flinta",
+      "mixed_abilities"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / from / description
      Previous value: -"Earliest date, YYYY-MM-DD. Default today."New value: +"Window start, YYYY-MM-DD. Default today. Includes events still running on or after this date; a past date also returns ended events."
    • changedInput schema / properties / to / description
      Previous value: -"Latest start date, YYYY-MM-DD."New value: +"Window end: the latest start date, YYYY-MM-DD."
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is carried. The description adds genuinely new behavior: capped at 20 results, sorted by start date, each row containing id and a citreasurehunt.com URL, plus a total match count. It does not discuss empty-result behavior or ranking, which keeps it short of a 5.

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 purpose, then usage examples, then filters, then return shape and the sibling routing — a sensible order with no throwaway sentences. The domain noun list in sentence one is long but earns its place for term matching.

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, and the description compensates by stating the result shape (id, URL, start-date sort, total count, 20 cap). With zero required parameters and full schema coverage, the description plus schema is close to complete; only failure/empty-result handling is unaddressed.

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

Parameters3/5

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

Schema description coverage is 100%, so all nine parameters, including the past-date semantics of 'from' and the all-of semantics of 'features', are already documented. The description only restates the filter axes (country, city, dates, type, practice, free text) at a higher level, adding little beyond 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?

Specific verb + resource ("Find Contact Improvisation events worldwide") with the domain's event taxonomy enumerated (festivals, workshops, jams, classes), so the agent knows exactly what corpus this searches. It also distinguishes itself from the sibling that shares the same resource by routing detail lookups to get_event.

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?

Gives concrete when-to-use examples ("CI festivals in Germany this summer", "workshops with <teacher>", "when was X last year") and an explicit boundary: this tool returns summary rows, while get_event is the call for prices, teachers and full descriptions. Default behavior (upcoming unless a past 'from' is supplied) is stated up front.

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

All CI Treasure Hunt 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