Wai

House on a plot with pool, garage and the full report (Wai)

wai_design_house

Read-only

Wai's rule engine fits a villa, duplex or triplex villa (L-shaped, U round a courtyard, or compact for a small plot; optional basement) on a real plot with a swimming pool, a garage, storage and a perimeter wall or fence, and returns the report: site checks (setbacks, TAKS, KAKS, height), excavation and earthworks (m³, truck loads), the ground investigation to ask for, heat loss / gain and energy on the site climate, MEP for a house (heat pump or boiler, underfloor heating, split cooling, hot water, plumbing flows, electrical maximum demand and supply, PV potential), site hazards, the permits of the local authority (TR, RO or generic) and the bill of quantities - civil, mechanical, electrical. Cost only with the user's own unit rates (unit_rates {key: rate}, currency) - Wai gives no prices. Pre-design screening; the georeferenced IFC4 is in Wai. Answer with the returned numbers, not an estimate made before the call.

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": "wai_design_house"
  }
}

Input Schema

Name	Required	Description
`lat`	No
`lng`	No
`form`	No
`pool`	No
`gfa_m2`	No
`parcel`	No
`country`	No	ISO code, e.g. TR, RO
`far_max`	No
`storage`	No
`storeys`	No	1 villa, 2 duplex, 3 triplex
`basement`	No
`bedrooms`	No
`currency`	No
`perimeter`	No
`setback_m`	No
`parcel_l_m`	No
`parcel_w_m`	No
`unit_rates`	No	own unit rates by BoQ key, e.g. {"concrete": 120, "rebar": 900, "excavation": 8}
`garage_cars`	No
`coverage_max`	No
`height_max_m`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already mark this as a safe, read-only, open-world call, and the description adds real behavior beyond them: no prices are produced, cost only appears if the caller supplies unit_rates, and the georeferenced IFC4 lives in Wai rather than being returned. Since there is no output schema, the enumeration of report sections (site checks, earthworks, ground investigation, MEP, permits, BoQ) also carries the return-shape burden; failure behavior on an unusable parcel is the remaining gap.

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

Conciseness3/5

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

The core is front-loaded, but the opening sentence is a long parenthetical run-on that nests report sections, and the cost rule is buried mid-sentence. A short bulleted split between 'inputs it fits' and 'what it returns' would lose nothing and gain scanability.

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

Completeness4/5

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

For a 21-parameter, output-schema-less computation tool, the description covers the output surface thoroughly, states the no-prices rule and the IFC4 location, which is exactly what the agent needs to answer. The gap is input guidance: it never explains how to choose between the coordinate, polygon and width/length ways of describing the plot.

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?

With 21 parameters and only 14% schema description coverage, the description does real work: it clarifies pool, garage, storage, perimeter wall/fence, basement, the L/U/block form choice, TAKS/KAKS, height and setbacks. It leaves several parameters unexplained, notably the alternative site inputs (lat/lng vs. parcel polygon vs. parcel_l_m/parcel_w_m), gfa_m2 and bedrooms. That partial compensation supports a 3, not higher.

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 names a concrete verb and resource: a rule engine that fits a villa/duplex/triplex house on a real plot and returns a full design and cost report. It enumerates the report sections, so the agent knows exactly what the call produces. It never names a sibling (e.g. wai_design_building for other building types), so differentiation is inferred from 'villa, duplex, triplex' rather than stated.

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 says when to use it ('Pre-design screening') and instructs the agent to answer from returned numbers, not prior estimates. What is missing is the negative case: no exclusion telling the agent to use wai_design_building, wai_building_energy or wai_calculate instead for other building types or sub-analyses.

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

All Wai 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?