What's on in any city: live, ranked concerts, sport, festivals, nightlife and culture.
Scored across 3 tools
The three tools have clearly distinct purposes: get_event retrieves a single event by ID or URL, search_events discovers events, and list_cities provides coverage information. There is no overlap or ambiguity in their roles.
All tool names follow a consistent snake_case verb_noun pattern: get_event, list_cities, search_events. The pattern is predictable and easy to understand.
With only three tools, the server is well-scoped for a read-only event discovery service. Each tool serves a distinct essential function—search, detail retrieval, and city listing—without redundancy.
The toolset covers the core event discovery workflow: finding cities, searching events, and getting full event details. Minor gaps exist, such as no dedicated tool for browsing events by venue or category, but the name filter in search_events partially addresses this.
Get one event in full: description, venue and address, coordinates, local start and end, score with its reason, and the ticketing or official source page. Pass an id from search_events, or an event URL from placetobe.cc.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The event id, or its placetobe.cc/place/... URL. |
| Name | Required | Description |
|---|---|---|
| id | Yes | Stable event id (use with get_event). |
| lat | Yes | |
| lng | Yes | |
| url | Yes | The event's page on placetobe.cc. |
| area | Yes | Neighbourhood or area of the venue. |
| city | Yes | |
| tier | Yes | The score as a word: Legendary, Hot right now, Rising, Notable or On the radar. |
| when | Yes | Local date and time at the event, e.g. 'Sat 3 Oct, 20:00'. |
| image | Yes | |
| score | Yes | How big a moment it is (expected crowd and timing). |
| title | Yes | |
| venue | Yes | |
| reason | Yes | One line on why it scores as it does. |
| status | Yes | |
| address | Yes | |
| country | Yes | |
| ends_at | Yes | End, ISO 8601, when published. |
| category | Yes | |
| subtitle | Yes | |
| timezone | Yes | IANA time zone of the venue. |
| starts_at | Yes | Start, ISO 8601. |
| source_url | Yes | The ticketing or official page the listing came from. |
| attribution | Yes | |
| description | Yes | The source's description, trimmed. |
| time_announced | Yes | False when the source published a date but no start time. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered structurally. The description adds that results are drawn from placetobe.cc pages, but says nothing about failure behavior for an invalid/expired id, rate limits, or access requirements. Useful but not rich beyond what the annotations supply.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences: the first front-loads what the tool returns, the second handles input provenance. No filler, no repetition of the title, and the most decision-relevant content leads.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, the description need not document return values, and annotations cover the read-only profile; input sourcing is covered. What is missing is only edge-case behavior (invalid id, unknown URL), which is a minor gap for a single-parameter lookup.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, and the schema itself already documents the accepted id and URL formats. The description goes marginally further by naming the upstream producer (search_events) and the domain, which helps the agent construct a valid call when chaining tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('Get one event in full') and enumerates exactly what comes back: description, venue/address, coordinates, times, score with reason, and source page. This distinguishes it cleanly from the sibling search_events, which returns many events rather than one detailed record.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent where the input comes from — an id produced by search_events, or a placetobe.cc URL — which is the key chaining instruction. It lacks an explicit when-not-to-use note (e.g., 'do not use for browsing'), but the context is unambiguous for a detail-lookup tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the cities that currently have a live events board, with how many upcoming events each holds, biggest first. Filter by part of a name or by country. Use it to check coverage or to find the exact city name before calling search_events.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | Part of a city name, e.g. "san" or "York". | |
| country | No | English country name or ISO 3166-1 alpha-2 code. |
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| cities | Yes | |
| total_cities | Yes | Cities with a live board, before filtering. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the useful behavioral detail of result ordering (largest event count first) and that only cities with a live board are returned. It does not mention the default/max result count behavior, but that is minor against the annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler, with the what/ordering stated first and the routing/usage guidance second. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return-value structure need not be explained. Given a read-only, annotation-covered list tool with three simple params, the description supplies everything an agent needs to select and call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 67%, and the description reinforces the two documented filters (partial name match, country) but adds no new syntax or format detail beyond the schema. The 'limit' parameter is undocumented in both the description and the schema, so the description does not compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource ('List the cities that currently have a live events board') plus scope and ordering ('biggest first'), so the agent knows exactly what comes back. It also differentiates itself from the sibling search_events by framing itself as a coverage/name-resolution lookup rather than an event search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit when-to-use guidance ('Use it to check coverage or to find the exact city name before calling search_events'), naming the sibling it feeds into. The filtering options (part of a name, country) are also tied to concrete intent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find the events worth going to in a city, a country or worldwide, ranked by how big a moment each is (a 0-100 score from expected crowd and timing) or by start time, optionally only those matching a name (an artist, team, show or venue). Covers concerts, sport, festivals, nightlife, culture and city moments, merged from ticketing, sports and open-data feeds and refreshed every two hours. Use it for questions like "what's on in Lisbon this weekend", "biggest concerts in London this week", "when are Arsenal at home" or "is Coldplay playing in Europe". Each result has the local date and time, venue, score with a one-line reason, and a link to the event's page.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | City name in English, e.g. "London", "New York", "Mexico City". Add the country after a comma when a name is shared ("Paris, France"). Omit city and country for worldwide. For the major cities, results also include the big events just outside the city line (SoFi Stadium in Inglewood for Los Angeles, MetLife Stadium for New York); each result names its own town. | |
| sort | No | biggest: highest score first. soonest: earliest start first. | biggest |
| when | No | now: on right now. tonight: the rest of today, local time. this_weekend: Friday 17:00 to Sunday night, local time. this_week: the next 7 days. upcoming: the next 160 days. | upcoming |
| limit | No | How many events, 1 to 25. | |
| query | No | Only events whose title or venue contains this text: an artist, team, show or venue name, e.g. "Coldplay", "Arsenal", "Madison Square Garden". At least 2 characters. | |
| country | No | A whole country instead of one city: English name or ISO 3166-1 alpha-2 code ("Netherlands", "NL"). Ignored when city is given. | |
| categories | No | Only these kinds of events. Omit for all. |
| Name | Required | Description |
|---|---|---|
| sort | Yes | |
| when | Yes | |
| count | Yes | |
| query | Yes | The name filter, when one was given. |
| scope | Yes | Where: a city, a country, or 'worldwide'. |
| events | Yes | |
| board_url | Yes | The live board for this place on placetobe.cc. |
| attribution | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real value beyond that: the data is merged from ticketing, sports and open-data feeds and refreshed every two hours, and each result carries a local date/time, venue, score with a one-line reason, and a link. It does not discuss the limit/truncation behaviour, but the provenance and freshness disclosure is substantial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded paragraph that leads with the core action and scope before ranking, coverage and examples. It is dense but each clause carries information; the result-shape sentence is partly redundant given the output schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With seven optional parameters, an output schema, and read-only annotations, the description supplies what the structured fields do not: when to use the tool, the meaning of the ranking, data sources and refresh cadence, and example questions. An agent has everything needed to call it correctly without opening the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds meaning above the schema by explaining what the score driving "biggest" is (0-100 from expected crowd and timing) and by characterizing the query match (artist, team, show or venue), which helps the agent map natural-language requests onto the sort/query parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("find events"), the scope (city, country, worldwide), the ranking basis (0-100 moment score or start time), and the covered event types. It is clearly differentiable from get_event (a single event) and list_cities (a look-up of supported places).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives concrete usage context via example questions ("what's on in Lisbon this weekend", "when are Arsenal at home") and notes optional name filtering, which tells the agent when this tool fits. It stops short of explicitly naming when to prefer a sibling such as get_event for detail on one event.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_events1 field changedInput schema / properties / city / descriptionPrevious value: -"City name in English, e.g. \"London\", \"New York\", \"Mexico City\". Add the country after a comma when a name is shared (\"Paris, France\"). Omit city and country for worldwide."New value: +"City name in English, e.g. \"London\", \"New York\", \"Mexico City\". Add the country after a comma when a name is shared (\"Paris, France\"). Omit city and country for worldwide. For the major cities, results also include the big events just outside the city line (SoFi Stadium in Inglewood for Los Angeles, MetLife Stadium for New York); each result names its own town."get_eventlist_citiessearch_eventsLive event discovery: concerts, club nights, art, comedy, and festivals across 14 cities.
250,000+ real, local, future events, ranked for the signed-in person. Free to connect.
Live-concert discovery: 44,000+ upcoming concerts worldwide by city, artist, genre or festival.
Search live events in 60+ countries, plan a night out, and demand artists to tour your city.
Add one secure layer between your agents and this server.
