Skip to main content
Glama
This connector has been deprecated

Superseded by the canonical Dim Hour connector at https://glama.ai/mcp/connectors/com.dimhour.mcp/dim-hour (same server on its branded domain).

Search menus

search_menus
Read-only

Find dishes and drinks by name on the menus Dim Hour has verified from venues' own sites, in one city. Each result names the venue, the dish, its printed price (null when the menu prints none), the menu and section, and source_line, the same source and check date the venue page prints. Only verified menus are searched: a venue whose menu nobody has verified never appears, so zero results means no verified menu lists the dish, not that no venue serves it. Terms match at word starts, in the dish name first and then its description (matched_in says which). Optional filters: max_price keeps rows whose ONE printed price is at or under it (a row with no printed price, or several, never matches and is counted in unpriced_excluded); kind is food or drink; menu matches the printed menu name, e.g. 'happy hour'. total_matches counts the filtered rows. Past 90 days a menu is stale and its rows say so. At most 50 results per call; truncated says how many more matched. Prices and dishes change: confirm with the venue before relying on them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "city": "<city>",
      "query": "<query>"
    },
    "name": "search_menus"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityYesCity name or key
kindNoOnly food or only drink sections
menuNoPrinted menu name, e.g. 'happy hour', 'brunch'
limitNoResults to return (default 20)
queryYesA dish or drink, e.g. 'guacamole', 'espresso martini'
max_priceNoHighest printed price, in the menu's currency, e.g. 12

Output Schema

NameRequiredDescriptionDefault
cityYes
queryYes
termsYes
statusYes
filtersNo
reasonsYes
receiptYes
resultsYes
skippedYes
city_nameYes
truncatedNo
snapshot_idYes
total_matchesYes
policy_versionYes
venues_matchedYes
venues_searchedYes
stale_after_daysYes
unpriced_excludedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / kind
      Added value: +{
      +  "description": "Only food or only drink sections",
      +  "enum": [
      +    "food",
      +    "drink"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / max_price
      Added value: +{
      +  "description": "Highest printed price, in the menu's currency, e.g. 12",
      +  "exclusiveMinimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / menu
      Added value: +{
      +  "description": "Printed menu name, e.g. 'happy hour', 'brunch'",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedOutput schema / properties / filters
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "kind": {
      +      "enum": [
      +        "food",
      +        "drink"
      +      ],
      +      "type": "string"
      +    },
      +    "max_price": {
      +      "type": "number"
      +    },
      +    "menu": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / results / items / properties / kind
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "food",
      +        "drink"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
    • changedOutput schema / properties / results / items / required
      Previous value: -[
      -  "id",
      -  "venue",
      -  "address",
      -  "dish",
      -  "price",
      -  "description",
      -  "matched_in",
      -  "menu",
      -  "menu_type",
      -  "section",
      -  "currency",
      -  "source_line",
      -  "source_url",
      -  "verified_at",
      -  "freshness",
      -  "age_days"
      -]New value: +[
      +  "id",
      +  "venue",
      +  "address",
      +  "dish",
      +  "price",
      +  "description",
      +  "matched_in",
      +  "kind",
      +  "menu",
      +  "menu_type",
      +  "section",
      +  "currency",
      +  "source_line",
      +  "source_url",
      +  "verified_at",
      +  "freshness",
      +  "age_days"
      +]
    • addedOutput schema / properties / unpriced_excluded
      Added value: +{
      +  "type": "number"
      +}
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare readOnly/openWorld=false/destructive=false; the description adds substantial behavior: word-start term matching with matched_in reporting, verified-only corpus, max_price excluding rows with no price or multiple prices (counted in unpriced_excluded), 90-day staleness flagging, and a 50-result cap with truncated. It even warns that prices and dishes change and should be confirmed with the venue.

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?

The purpose and scope are front-loaded and nearly every clause carries information. It is a dense single block, though, and would scan better as short labeled clauses; the closing caution about confirming with the venue is useful but slightly tacked on.

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 6-parameter filtered search with an output schema and safety annotations, the description covers corpus scope, matching rules, filter edge cases, result shape fields, truncation, staleness, and a caveat about data freshness. Nothing an agent needs to call it correctly or interpret results is missing.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds semantics the schema cannot: query matches at word starts against dish name first then description, menu matches the printed menu name (e.g. 'happy hour'), max_price only applies to rows with exactly one printed price, and limit interacts with the 50-cap and truncated counter. This meaningfully changes how an agent should phrase queries and interpret empty results.

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?

The description opens with a specific verb+resource+scope: 'Find dishes and drinks by name on the menus Dim Hour has verified from venues' own sites, in one city.' It is clearly a dish-level menu search, distinguishable from venue-level siblings like search_venues or get_venue_menus without opening a 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?

Usage context is strong: it states only verified menus are searched and that zero results means no verified menu lists the dish, not that nobody serves it — a real interpretation guardrail. It also scopes the optional filters. What's missing is an explicit 'use X instead when…' routing against siblings such as search_venues or get_venue_menus.

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