Hospitality Radar

Find hotel projects

find_projects

Read-only

Search hotel projects by place, phase, class, size and opening year. Returns project descriptions without names (free, daily quota). Names are in the project file (quote_file, open_file).

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_projects"
  }
}

Input Schema

Name	Required	Description
`city`	No
`type`	No
`class`	No
`limit`	No
`phase`	No	construction = construction & fit-out, planning = planning & design, vision = vision & site, renovation
`offset`	No	At most 200. For more results, narrow the filters (country, city, class, opening year).
`region`	No
`country`	No	Country names in English or ISO codes, e.g. ["Spain", "PT", "United States"]
`min_keys`	No
`near_lat`	No
`near_lng`	No
`min_stars`	No
`near_city`	No	Radius search around this city, e.g. "Karlsruhe". Use with radius_km. Use near_lat/near_lng for places Radar does not know.
`radius_km`	No
`opening_to`	No	Opening year to
`roles_known`	No	Only projects whose file names a company in all these roles (names stay in the file). Use ["architect", "design studio"] for projects where interiors are being specified.
`near_country`	No	Country of near_city, if the name is ambiguous
`opening_from`	No	Opening year from
`signal_since`	No	Only projects with a signal on or after this date (YYYY-MM-DD)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds real behavioral context: results are returned without names, the call is free but subject to a daily quota, and names require opening the project file. That is exactly the kind of cost/redaction detail annotations cannot express. It omits anything about pagination behavior or result ordering, which keeps it from a 5.

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

Conciseness5/5

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

Three short sentences, front-loaded with what is searched, followed by what comes back and where the missing piece (names) lives. No redundant restatement of the title, no filler.

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?

For a 19-parameter tool with no output schema and 47% schema coverage, the description covers the return shape (unnamed descriptions) and the name-lookup follow-up, which is the most important gap. However it says nothing about the limit/offset cap of 200 or how to page beyond results, and most filter parameters are unexplained, so an agent still has to read the whole schema to call it well.

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 coverage is only 47%, so the description needs to compensate, and it partially does by naming the filter axes (place, phase, class, size, opening year). But several parameters such as min_keys, min_stars, roles_known, signal_since, and near_lat/near_lng are never explained in the description, and 'size' is an ambiguous gloss. It adds some orientation but leaves much of the 19-parameter surface to the schema.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Search hotel projects by place, phase, class, size and opening year.' It also separates this tool from the file-reading siblings by noting names live in the project file (quote_file, open_file). It does not distinguish itself from project_summary or new_signals, so it falls just short of a 5.

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?

It states when to reach for this tool (filtering projects) and explicitly routes the agent to quote_file/open_file when names are needed. The 'free, daily quota' note also signals it is the cheap first-pass tool. There are no explicit when-not conditions against siblings like project_summary.

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

All Hospitality Radar 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?