Skip to main content
Glama

Sirfus CAR

Send a request to one checked business

car_send_request

Starts a request for the signed-in person. Needs what they need, where (City, ST), and their consent. Returns a requestId. If CAR is not sure what kind of business it needs, it answers needs_detail with a question and choices and sends nothing; a repeat call with category set to one of those choices goes ahead. Status verify_person means the person was texted a 6-digit code, which car_confirm_person checks. No business is contacted before that.

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": {
      "what": "<what>",
      "where": "<where>",
      "consent": "<consent>"
    },
    "name": "car_send_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoFirst name the business can ask for
sizeNoSize of the job, e.g. "40 guests", "3 bedrooms"
whatYesWhat the person needs, in their own words. This text goes to the matched business, so it holds no health details, ID numbers, card numbers or passwords.
whenNoasap, this_week, flexible, or a date (YYYY-MM-DD)
whereYesCity and two-letter US state, e.g. "Tampa, FL" (a ZIP may follow)
budgetNoBudget, if the person gave one
consentYesThe person agreed to be contacted by one matched business and by CAR about this request
contactNo
categoryNoOptional. A category slug from /v1/categories that the person picked, for example after a needs_detail question. Without it, CAR reads the request.
estimateIdNoAn estimateId from car_get_estimate: the business gets the same scope and planning range
idempotencyKeyNo8-64 letters, digits, _ or -. A repeat with the same key returns the same request

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare openWorldHint=true, readOnlyHint=false and idempotentHint=false, so the externally-visible, mutating nature is known. The description adds real value with the gating flow: needs_detail sends nothing, verify_person means a 6-digit text code, and 'no business is contacted before that'. It does not mention idempotency behavior or what a failed/duplicate submission looks like at the description level.

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 the action and required inputs, then the exception paths, with zero filler. The phrasing 'Needs what they need' is slightly awkward and the sentences are telegraphic, but nothing is wasted.

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 an 11-parameter, nested-object, open-world mutation with no output schema, the description covers the required inputs, the deferred-confirmation branch, the verification step and the requestId return. Coverage of the contact/phone default and estimateId linkage is left to the schema, which is acceptable given 91% schema coverage.

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 description coverage is 91%, so the schema already documents what, where, consent, category and estimateId thoroughly. The description reinforces the required trio and links category to the needs_detail choices, but adds little syntax or semantics beyond what the schema provides. Baseline 3 is appropriate.

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?

States a specific verb and resource: starts a request for the signed-in person, with the three required inputs and a requestId return. The title anchors it to 'one checked business', which differentiates it from discovery siblings, though the word 'request' alone is a bit abstract without the title.

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?

Clearly explains the two conditional branches: an unresolved category yields needs_detail with choices and nothing is sent, and a repeat call with a chosen category proceeds. It points to car_confirm_person for verify_person, giving a concrete next step. It doesn't explicitly say when to prefer car_get_estimate first, though the estimateId field implies that path.

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