Skip to main content
Glama

Sirfus CAR

Find businesses outside the network

car_find_outside
Read-onlyIdempotent

Only when no signed-up Sirfus business fits the work and place: up to 3 businesses from public listings, each with where it was found, its public phone and website, a rating only when Google gave one, and availability only when known ("we'll confirm a time" otherwise). CAR contacts none of them and shares nothing about the person. Legal work is not listed; health work is listed by distance, not ranked. Returns a searchId for car_pick_outside.

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>"
    },
    "name": "car_find_outside"
  }
}

Input Schema

NameRequiredDescriptionDefault
whatYesWhat the person needs
whereYesCity and two-letter US state, e.g. "Tampa, FL"
categoryNoOptional. A category slug from /v1/categories that the person picked, for example after a needs_detail question. Without it, CAR reads the request.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already cover read-only/open-world/idempotent, and the description adds genuinely new behavioral facts: CAR contacts none of the listed businesses and shares nothing about the person, legal work is excluded entirely, health work is ordered by distance rather than ranked, and availability is only reported when known with a fixed fallback phrase. These are non-obvious constraints that materially change how an agent should present results.

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 gating condition is front-loaded, which is the right structure, and the parenthetical clauses replace longer sentences. It reads as one dense run-on sentence, so the rating-disclosure and health-ordering clauses take a second pass to parse, but no sentence is filler.

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?

With no output schema, the description carries the return-shape burden and does so: it enumerates the per-result fields, the rating and availability caveats, and the searchId handoff to car_pick_outside. An agent has everything needed to call it and to explain results correctly without further documentation.

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 100%, so the schema already documents 'what', 'where', and the optional 'category' slug. The description adds domain framing (the work and the place) but no new syntax, format, or validation detail beyond what the schema states, so baseline 3 applies.

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 — pulling up to 3 businesses 'from public listings' — and immediately scopes it against the in-network case ('no signed-up Sirfus business fits'), which is exactly the sibling distinction an agent needs. The parenthetical details (where found, phone, website, rating, availability) make the output shape of the result unmistakable.

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?

The leading clause 'Only when no signed-up Sirfus business fits the work and place' is a clear gating condition, and 'Returns a searchId for car_pick_outside' routes the agent to the natural follow-up. It stops short of naming the in-network search sibling explicitly as the preferred alternative, leaving the agent to infer which tool covers that case.

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