Skip to main content
Glama

A-du: ADU rentals, plans and rules

Search pre-approved ADU plans

search_plans
Read-onlyIdempotent

Search A-du Build, the marketplace of ADU plan sets listed by licensed architects and designers. Each result carries size, bedrooms, bathrooms, plan price, estimated build cost range, the designer, and the cities where the plan is already pre-approved (which shortens plan check). Use for "find me an ADU plan", "how much does a plan cost", "what pre-approved plans exist for ". Filter pre_approved_in by city name to prefer plans a city has already accepted. For one plan's description, exterior dimensions, permitting price, style, foundation and image, call fetch with plan:<id>. Each result has a url on a-du.homes; the page there offers a free test fit on the user's own lot. plan_pricing says how each plan is priced: "free" (a city or county publishes it free, and plan_price_usd is 0), "fixed" (plan_price_usd is the designer's price) or "price_on_claim" (a designer's plan with no price on A-du yet: it has no plan_price_usd and is not free). Example: {"bedrooms_min": 1, "max_sqft": 800, "pre_approved_in": "Los Angeles"}.

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_plans"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoResults per page, 1 to 50.
cursorNoOpaque cursor from a previous response.
max_sqftNo
min_sqftNo
bedrooms_minNo
max_plan_priceNoMaximum price of the plan set itself in US dollars, not the build cost. Keeps free plans and plans priced at or under it; plans with no listed price are left out.
pre_approved_inNoCity name. Keeps plans whose pre-approval list mentions it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / max_plan_price / description
      Previous value: -"Maximum price of the plan set itself in US dollars, not the build cost."New value: +"Maximum price of the plan set itself in US dollars, not the build cost. Keeps free plans and plans priced at or under it; plans with no listed price are left out."
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description focuses on what the agent actually can't infer: the exact fields returned per result, the meaning of the url/free test-fit page, and a careful definition of plan_pricing states including the 'price_on_claim' edge case where plan_price_usd is absent and the plan is not free. That last point materially changes how an agent should interpret results. It stops short of describing pagination/limit behavior beyond the schema, so not 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.

Conciseness4/5

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

Front-loaded with purpose before detail, and most sentences map to a decision the agent must make (which sibling, which filter, how to read pricing). It is on the long side and the plan_pricing taxonomy plus the trailing example add bulk, but neither is filler — both resolve ambiguity in the returned data.

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?

There is no output schema, so the description carries the full burden of telling the agent what comes back, and it does: size, bedrooms, bathrooms, plan price, build cost range, designer, pre-approved cities, and a url. Combined with the sibling routing to `fetch` and the pricing-state definitions, an agent has everything needed to call this and interpret results.

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?

Schema coverage is 57%, so the description must carry some weight and it does: it clarifies that pre_approved_in takes a city name and means the plan appears on that city's pre-approval list, and it disambiguates plan price from build cost ('not the build cost', free plans retained, unpriced plans excluded). The worked example combines bedrooms_min, max_sqft and pre_approved_in into a realistic call. min_sqft and bedrooms_min are left to the schema, hence 4 rather than 5.

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?

Opens with a specific verb and resource ('Search A-du Build, the marketplace of ADU plan sets') and immediately differentiates itself from the sibling `fetch` by stating that per-plan detail (description, dimensions, images) lives there instead. An agent can distinguish this from search_rentals, search_managers, or match_plans_to_lot 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?

Provides explicit trigger phrases ('find me an ADU plan', 'how much does a plan cost', '<city> pre-approved plans') and a concrete alternative with its condition: use `fetch` with `plan:<id>` when you need one plan's full detail. It also gives a selection heuristic (filter pre_approved_in to prefer already-accepted plans), which is when-to-use guidance at the level of a decision rule.

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