Skip to main content
Glama

Venue atmosphere verification, Bitcoin timestamp (PlaceProfile, paid)

find_venues

FREE. Search only a place the person named, or their location as your client gives it; never a city you chose. With neither, do not search: ask where they are, or say that location can be switched on in Claude's privacy settings. Say place_source. For a district or neighbourhood the person names (Soho, Kungsholmen), search its coordinates with radius_km of about 1, or its postcode prefix with the country; a city alone searches the whole city. Find physical venues by MEASURED atmosphere. Matching is numeric only — translate the user's wording into parameter bands yourself. Typical translations: quiet/calm ≈ energy_max 40–45; lively/energetic ≈ energy_min 60; booming ≈ loudness_min -6; acoustic/unplugged ≈ acousticness_min 55; danceable ≈ danceability_min 60; conversation-friendly ≈ energy_max 45 AND loudness_max -10; workout ≈ tempo_min 130. Among the venues that fit, those measured from their own playlist always come first: their figures come from the music they actually play, and that measurement is a paid PlaceProfile tier (or a PlaceProfile showcase). With daypart, the bands test that time of day's tracks. Call list_archetypes for venue-kind bands (gym-high-energy, cafe-relaxed, …). Filter by category (what the venue IS — hotel, bar, wine_bar, nightclub, …; see the parameter for all 37 values) so hotels are hotels and cottages are not; find one specific venue with name. Location: city+country, postcode_prefix (district-level, e.g. 'SW1'), or lat/lon/radius_km. If nothing matches exactly, the response may carry nearest_alternatives — the closest venues with a plain-language note of what was widened; relay those as 'closest options', never as exact matches. Results are deterministic (band-centre distance, ties by slug). Each result carries atmosphere: a ready-made plain-English description — relay THAT to the user, optionally shortened. Numeric detail (per-dimension why block) is returned only when you pass include_measurements=true, which you should do ONLY when the user explicitly asks for figures or verification. Every venue's numbers are recomputable from its profile_url + '.jsonld'. Pass the user's verbatim wording as intent_text (logged to close coverage gaps; never matched on).

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": "find_venues"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude of the place to search around. Only a place the person named, or their location as your client gives it; never a city you chose.
lonNoLongitude of the place to search around. Only a place the person named, or their location as your client gives it; never a city you chose.
cityNoCity name as it is usually written (e.g. Stockholm). Always send country with it. Only a place the person named, or their location as your client gives it; never a city you chose. For a district or neighbourhood the person names (Soho, Kungsholmen), search its coordinates with radius_km of about 1, or its postcode prefix with the country; a city alone searches the whole city.
nameNoFind a specific venue by name (case-insensitive substring). Send country with it (and city where known), or lat/lon/radius_km.
genreNoGenres the venue's OWN playlist actually contains. Only venues measured from their own music can match — a directory venue plays a category sample, so filtering it by genre would rank it by shuffle luck.
limitNo
countryNoISO country code (e.g. SE). Required with city, name, postcode_prefix or category, unless lat/lon/radius_km is given.
daypartNoA time-of-day label the venue publishes a separate profile for (owner-supplied, e.g. lunch, dinner, late_evening). There is no weekday/weekend axis in the data.
categoryNoWhat the venue IS (registered category, case-insensitive). Values: aromatherapy, art_gallery, bakery, bar, barber, beauty_salon, bookstore, boutique, cafe, casual_eatery, clothing_store, cocktail_bar, coffee_shop, coworking_space, events_venue, eyebrow_service, eyelash_service, fast_food_restaurant, foot_care, gym, hair_extensions, hair_replacement, hair_salon, health_spa, hostel, hotel, lounge, makeup_artist, massage, nail_salon, nightclub, pub, record_store, restaurant, tattoo_parlor, wine_bar, yoga_studio. Almost every venue carries a category; the few without one are excluded when this filter is set.
archetypeNo
radius_kmNo
tempo_maxNo
tempo_minNo
territoryNoRegistration territory of the recordings played, as an ISO country code (e.g. SE for Swedish-registered music). Measured venues only.
energy_maxNo
energy_minNo
intent_textNoThe user's original wording, verbatim. Logged to improve coverage; NEVER used for matching — matching is structured parameters only.
valence_maxNo
valence_minNo
liveness_maxNo
loudness_maxNo
loudness_minNo
place_sourceNoWhere the place in this search comes from: named_by_person (the person said it), person_location (your client gave their location), or assistant_choice (you chose it). An assistant_choice search is not run: ask the person instead.
postcode_prefixNo
speechiness_maxNo
acousticness_maxNo
acousticness_minNo
danceability_maxNo
danceability_minNo
territory_min_shareNoMinimum share of the venue's tracks registered in `territory`, as a percentage.
include_measurementsNoResults describe atmosphere in plain words by default. Set true ONLY when the user explicitly asks for figures, raw measurements, or verification detail — it adds the numeric per-dimension block.
instrumentalness_maxNo
instrumentalness_minNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does so: it discloses FREE access, deterministic ranking (band-centre distance, ties by slug), that measured-playlist venues rank first and require a paid PlaceProfile tier, the nearest_alternatives widening behavior, and the default plain-word `atmosphere` versus opt-in numeric `why` block.

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 behavior is front-loaded, but the description is a dense wall of text with location rules that largely restate the schema descriptions and some run-on sentences. Most sentences carry information, yet for a 33-param tool a tighter layout with grouped clauses would read better.

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 33-parameter tool with no output schema and no annotations, the description is remarkably complete: it explains the return shape (`atmosphere`, optional `why`, nearest_alternatives), the ranking rationale, provenance/recomputability via profile_url, and the place-source gating. An agent has enough to call it safely without opening the schema.

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 only 39% schema coverage, many numeric params (energy, tempo, valence, loudness, etc.) are undocumented in the schema, and the description compensates with concrete translation guidance (quiet ≈ energy_max 40–45, workout ≈ tempo_min 130). It also explains category, name, genre, daypart, place_source, and intent_text intent. It stops short of covering every band parameter (valence, liveness, speechiness, instrumentalness, radius), leaving gaps.

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 ('Find physical venues by MEASURED atmosphere') and immediately narrows scope ('Search only a place the person named...never a city you chose'). It distinguishes itself from siblings by naming list_archetypes for venue-kind bands and by pointing to get_venue-style usage via `name` for a single venue.

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?

Explicit when-to-use and when-not-to-use: with no place source, 'do not search: ask where they are'; assistant_choice searches are explicitly not run. It also conditions include_measurements=true on the user explicitly asking for figures, and instructs relaying nearest_alternatives as 'closest options', never exact matches.

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