Skip to main content
Glama

Find homes that fit

find_homes
Read-onlyIdempotent

Checks the homes for sale in Sydney that Sagashi holds against a buyer's answers, and returns how many fit and the newest that do, each naming the answers it matched and linking to its source. Set only what the buyer said. Get suburbs from find_suburb, school codes from find_school and a place to travel to from find_place first. A driving or cycling trip is not checked here. Say only what Sagashi returned: when nothing fits, say so, without guesses about the market.

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": {
      "profile": "<profile>"
    },
    "name": "find_homes"
  }
}

Input Schema

NameRequiredDescriptionDefault
profileYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / profile / properties / ideal
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "text": {
      -      "anyOf": [
      -        {
      -          "maxLength": 600,
      -          "type": "string"
      -        },
      -        {
      -          "type": "null"
      -        }
      -      ],
      -      "description": "The buyer's own words about the home they want. Kept as written; it changes no verdict. Leave it out unless the buyer said it."
      -    }
      -  },
      -  "type": "object"
      -}
  2. Changed5 schema fields changed
    • changedInput schema / properties / profile / properties / commute / properties / arriveBy / description
      Previous value: -"The time to arrive by, 24-hour \"HH:MM\". Leave it out unless the buyer said it."New value: +"The time to arrive by, 24-hour \"HH:MM\". Needed for the public transport trip to be checked. Leave it out unless the buyer said it."
    • changedInput schema / properties / profile / properties / commute / properties / maxMinutes / description
      Previous value: -"The longest the trip may take, in minutes. Only a public transport (\"Transit\") trip rules homes out. Leave it out unless the buyer said it."New value: +"The longest the trip may take, in minutes. Only a public transport (\"Transit\") trip rules homes out. Needed for the public transport trip to be checked. Leave it out unless the buyer said it."
    • changedInput schema / properties / profile / properties / commute / properties / mode / description
      Previous value: -"How the buyer travels. A driving or cycling trip is not checked here and rules nothing out. Leave it out unless the buyer said it."New value: +"How the buyer travels. A driving or cycling trip is not checked here and rules nothing out. Needed for the public transport trip to be checked. Leave it out unless the buyer said it."
    • changedInput schema / properties / profile / properties / schools / properties / travelTo / description
      Previous value: -"Kinds of school the buyer wants nearby. With schools.within set, a home with none that close is ruled out. Leave it out unless the buyer said it."New value: +"Kinds of school the buyer wants nearby. With schools.within set, a home with none that close is ruled out. Needs schools.within for the distance to be checked. Leave it out unless the buyer said it."
    • changedInput schema / properties / profile / properties / schools / properties / within / description
      Previous value: -"How far, in a straight line, the nearest school of a kind in schools.travelTo may be. Leave it out unless the buyer said it."New value: +"How far, in a straight line, the nearest school of a kind in schools.travelTo may be. Needs schools.travelTo for the distance to be checked. Leave it out unless the buyer said it."
  3. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real behavioral context beyond that: it discloses the result shape (count plus newest matches with source links) and the limitation that drive/cycle commutes rule nothing out. It stops short of covering pagination or result caps, which keeps it at a 4.

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 what the tool does and returns, then prerequisites, then the exclusion, then the reporting rule. Sentences are dense but nearly all earn their place; the closing instruction about not guessing about the market is useful but adds a little length beyond tool selection.

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 deep nested-schema tool with no output schema, the description covers the essentials: what is matched, what comes back, which sibling tools provide prerequisite identifiers, which inputs are ignored for verdicts, and how to report an empty result. Nothing critical for a correct call is missing.

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?

Reported schema coverage is 0%, but the description compensates with cross-parameter meaning: only a Transit trip with destination coordinates from find_place produces a verdict, suburbs must be spelled as find_suburb returns them, and school zones must be four-digit codes from find_school. It does not walk through the profile fields themselves, so a 4 rather than a 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?

Specific verb and resource: 'Checks the homes for sale in Sydney that Sagashi holds against a buyer's answers', plus the return shape (how many fit, the newest that do, each naming matched answers and linking to source). This clearly separates it from home_details (one home) and the find_* lookup tools.

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?

Explicit prerequisites and alternatives: get suburbs from find_suburb, school codes from find_school, destinations from find_place before calling. It also states an exclusion ('a driving or cycling trip is not checked here') and a response rule ('when nothing fits, say so, without guesses about the market').

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