Foobos: Boston and Denver concerts and comedy

Shows tonight

shows_tonight

Read-onlyIdempotent

Concerts and comedy tonight and the next two days in Boston (default) or Denver (city=denver), in the city's own time zone. Use this for “what's on tonight?”, “anything going on?”, “live music near me tonight”. Default sort=evening: evening and upcoming first, not brunch-first chrono. sort=time for raw order; sort=popular bumps editorial picks. For “what’s free tonight?” set free=true or call shows_free. For “what should I see?” or date night call list_picks. Always cite url (/e/?id=). Do not rewrite to /event/. Returns a page of shows (default 20, max 50) plus total. Page with offset; never ask for the full tonight list (~174 shows / ~36k tokens).

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": "shows_tonight"
  }
}

Input Schema

Name	Required	Description	Default
`via`	No	Inbound UTM source written onto every Foobos deep link. Default muse.
`area`	No	Finder WHERE pill or neighborhood (Boston: cambridge, allston_brighton, somerville…; Denver: den_downtown, den_colfax, boulder…). Aliases: neighborhood, where.
`city`	No	boston (default: Boston, Cambridge, Somerville, Greater Boston) or denver (Denver, Boulder, the Colorado Front Range). Set denver for anything in Colorado.	boston
`free`	No	If true, only free shows (listing flag or price 0). Use for “what’s free tonight?”. Alias: is_free.
`mbta`	No	Boston only. If true, only MBTA-accessible rooms.
`sort`	No	evening (default): evening + upcoming first, not brunch-first chrono. time: raw chronological. popular: editorial picks first, then evening.	evening
`genre`	No	Finder mega-category (rock, punk, pop, jazz, soul, blues, folk, electronic, hiphop, reggae, classical, latin). Alias: genres. Comedy is event_type, not a genre. Joined from finder.json `g` — do not invent tags.
`large`	No	Hint alias of min_capacity=5000.
`limit`	No	Page size. Default 20, max 50. Do not request the full list — tonight is ~174 shows / ~36k tokens.
`genres`	No	Comma-separated megas. Alias of genre.
`is_new`	No	If true, only just-added (finder new).
`offset`	No	Rows to skip. Use with the returned total to page.
`is_free`	No	If true, only free shows (listing flag or price 0). Use for “what’s free tonight?”. Alias: is_free.
`all_ages`	No	If true, only all-ages (a/a).
`intimate`	No	Hint alias of max_capacity=500. Unknown capacity excluded.
`max_price`	No	Numeric price ceiling. Free passes; unknown price excluded.
`event_type`	No	comedy or music. Comedy is public event_type / finder ty=c, NOT a genre tag. Use for “comedy this week?”.
`max_capacity`	No	Known venues.json capacity ≤ N. intimate=true aliases max_capacity=500 (hint, not a stored flag).
`min_capacity`	No	Known venues.json capacity ≥ N. large=true aliases min_capacity=5000.
`neighborhood`	No	Alias of area.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already establish a safe, idempotent, non-destructive read, and the description adds operational behavior the annotations cannot: a stable default ordering that is not raw chronological, time-zone handling, page-size ceilings, and a concrete token/size warning (~174 shows, ~36k tokens) that discourages dumping the full list. It also imposes output-citation rules (always cite `url`, never rewrite to /event/), which is useful behavioral context. It falls short of 5 only because it doesn't describe response fields beyond 'a page of shows plus total'.

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 scope before tool-routing, then behavior, then pagination safety — a sound order. It is dense to the point of terseness in places ("not brunch-first chrono") and repeats the ~174-show/36k-token warning that also appears in the `limit` schema description, which is a small redundancy.

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 20-parameter, zero-required tool with no output schema, the description covers geography defaults, ordering behavior, return shape and pagination via offset/total, and output citation requirements. An agent has everything needed to call it correctly and avoid the main failure mode of over-fetching.

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% across all 20 parameters, so the schema already explains city defaults, sort modes, free filtering, and capacity hints. The description's parameter-level content (default Boston, city=denver, sort=evening semantics, free=true) largely restates the schema rather than adding new meaning, so the baseline 3 applies.

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 resource (concerts and comedy), a precise time window (tonight and the next two days), and default geography (Boston, with Denver via city=denver) including time-zone semantics. This is clearly separable from shows_free, list_picks, and shows_this_weekend without opening any schema.

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?

Enumerates the exact user phrasings that select this tool ("what's on tonight?", "live music near me tonight") and routes two competing intents elsewhere by name: free queries to shows_free or free=true, and "what should I see?"/date night to list_picks. Only a general when-not exclusion is absent, which is minor given the explicit sibling routing.

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

All Foobos: Boston and Denver concerts and comedy tools Inspect

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

Need Help?