JobJar: find a tradie

request_quotes

Destructive

Send one quote request to up to 3 local businesses at once (quotable: true from search_trades), so the customer doesn't have to ring around. Call with step 'check' first and show the customer the read_back; only after they agree, call again with step 'send' and identical details. If the person has connected JobJar (signed in once), it sends straight away with their verified mobile; otherwise they get a code or link on their own mobile or email and nothing reaches the businesses until they confirm. Each business replies to the customer directly with a price, a time to come and look, or 'not for me'.

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": {
      "listing_ids": "<listing_ids>",
      "step": "<step>",
      "job": "<job>",
      "suburb": "<suburb>",
      "postcode": "<postcode>",
      "customer_name": "<customer_name>"
    },
    "name": "request_quotes"
  }
}

Input Schema

Name	Required	Description
`job`	Yes	What needs doing, in the customer's words, with anything that helps price it (size, brand, age, access).
`step`	Yes
`suburb`	Yes
`timing`	No	When they need it, e.g. 'this week', 'urgent', 'no rush'.
`details`	No
`postcode`	Yes
`listing_ids`	Yes	Ids from search_trades, chosen by the customer.
`customer_name`	Yes
`customer_email`	No	If no mobile, or as well.
`customer_mobile`	No	Australian mobile. The confirm link and replies go here.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=false, destructiveHint=true, openWorldHint=true; the description goes well beyond by disclosing the two-step confirmation gate, that nothing reaches businesses before customer confirmation, the signed-in vs code/link verification paths, and that replies arrive directly to the customer. This is exactly the irreversibility and side-effect context the destructive hint implies but does not explain.

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?

The critical instruction (check before send) and the scope (up to 3 businesses) are front-loaded, and every sentence carries operational information. It is dense and some sentences pack multiple clauses, but there is no filler.

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 10-parameter, 6-required mutation with no output schema, the description covers the call flow, the gating condition, verification mechanics, and the expected outcome (businesses reply with price, visit time, or refusal). Minor gaps remain around the purpose of the details array and what the 'check' step actually returns, though the read_back is mentioned.

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 50%, and the description fills the most consequential gaps: it defines what the 'check' vs 'send' enum values mean and that details must be identical between the two calls, and it establishes provenance for listing_ids. It adds nothing for timing, details, suburb, postcode, or customer_email, which remain schema-only.

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?

States a specific verb and resource ('Send one quote request to up to 3 local businesses'), plus the customer-facing rationale. It also implicitly distinguishes itself from search_trades (source of listing_ids) and quote_status (reply tracking), so an agent can identify it without opening the 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?

Gives an explicit required sequence: call with step 'check' first, show the read_back to the customer, and only call 'send' after agreement with identical details. It also names the precondition for usable listing_ids ('quotable: true from search_trades') and explains the fallback path when JobJar isn't connected.

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

All JobJar: find a tradie 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?