Skip to main content
Glama

Côte Privée: private driver in Burgundy

Search places in Burgundy

search_places
Read-onlyIdempotent

Wine villages, châteaux, things to do and MICHELIN-starred restaurants: id, commune, drive and price by private driver from Beaune (per vehicle, one way / same-day return), the drive and fare from Paris and from Lyon airport (fromParis, fromLyon: the same both ways), the wine day of its page and its price, page and booking link; a restaurant's stars and cheapest menu (no opening days in the data). near and radiusKm: the places around a place, nearest first. 8 results unless limit; compact drops summaries.

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": "search_places"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNocote: Côtes de Nuits and de Beaune; north: Chablis, Yonne, Auxois; south: Chalonnais, Mâconnais.
kindNo
langNoar: Arabic notes, data in English.
nearNoA place id or name.
limitNo
queryNoWords in names, communes and summaries, e.g. "abbey", "grand cru".
compactNo
radiusKmNoDefault 10.

Output Schema

NameRequiredDescriptionDefault
nearNo
countYes
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / properties / results / items / properties / fromLyon
      Added value: +{
      +  "properties": {
      +    "km": {
      +      "type": "number"
      +    },
      +    "minutes": {
      +      "type": "number"
      +    },
      +    "oneWay": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "km",
      +    "minutes",
      +    "oneWay"
      +  ],
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / results / items / properties / fromParis
      Added value: +{
      +  "properties": {
      +    "km": {
      +      "type": "number"
      +    },
      +    "minutes": {
      +      "type": "number"
      +    },
      +    "oneWay": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "km",
      +    "minutes",
      +    "oneWay"
      +  ],
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / results / items / required
      Previous value: -[
      -  "id",
      -  "kind",
      -  "name",
      -  "commune",
      -  "area",
      -  "lat",
      -  "lon",
      -  "driveFromBeaune",
      -  "priceFromBeaune",
      -  "url",
      -  "bookUrl"
      -]New value: +[
      +  "id",
      +  "kind",
      +  "name",
      +  "commune",
      +  "area",
      +  "lat",
      +  "lon",
      +  "driveFromBeaune",
      +  "priceFromBeaune",
      +  "fromParis",
      +  "fromLyon",
      +  "url",
      +  "bookUrl"
      +]
  2. First observed

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already establish read-only, idempotent, closed-world behavior, so the bar is lower, and the description does add real context: pricing is per vehicle and one-way or same-day return, fromParis/fromLyon fares are symmetric, the default page size is 8, 'compact' drops summaries, and restaurant data has no opening days. Those are genuinely useful operational facts an agent cannot get from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The entire description is a single run-on sentence stitched together with semicolons and parentheses, with no front-loaded statement of what the tool does. Return-field enumeration consumes most of the text while the core action is never stated, so density comes at the cost of parseability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the long enumeration of returned fields is largely redundant and the space would be better spent on the search operation itself. With 8 optional parameters, no required inputs and no default sort or precedence rules stated (e.g. how near and query combine), the definition is adequate but leaves real gaps.

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?

Coverage is 63% and the description fills several gaps: it explains near/radiusKm behavior (nearest first, radius default 10 in schema), states the 8-result default unless limit is set, and defines what compact does. Its field-level notes also clarify that fromParis/fromLyon drive and fare apply identically in both directions. Only 'kind' and 'query' semantics remain purely schema-driven, which is acceptable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The resource is identifiable — wine villages, châteaux, sights and restaurants in Burgundy — but the description never opens with a verb+resource statement; it reads as a data dictionary of returned fields. The tool's actual job (search/filter places) must be inferred from the name and title, and nothing explicitly separates it from siblings like find_events or get_page.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage-like content is 'near and radiusKm: the places around a place, nearest first' and the default result count, which explain mechanics rather than when to choose this tool. There is no guidance on when to prefer plan_wine_day, get_prices or find_events instead, and no mention of required inputs or typical call patterns.

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