Skip to main content
Glama

See years and trims

see_car_choices
Read-only

Shows the model years and the trim levels Ridekick lists for one make and model. year and trim narrow the trims, and trimsYear is the model year the trims are for. A new-car ask starts here: a buyer who asks for a new car of a make and model, with or without a model year, and has named no listing. requests_preview follows it. A buyer can also name only a kind of car, such as a 3-row SUV. Each make and model of that kind is one call, and needs no ZIP code or model year. These are the choices Ridekick lists for the model: they carry no dollar amounts, colors or options, and they say nothing about whether a car is for sale near the buyer. With the buyer's ZIP code and the year it returns the same choices and also one yes or no, carsNearby, for whether a car like the one described is listed near the buyer. That answer has no count, dealership, town, distance or dollar amount, and it is not a promise that a car is for sale. The drivetrain and fuel lists are empty without a ZIP code. With one, they can name the types listed near the buyer, with no count. The exterior color is one of these: Black, White, Gray, Silver, Red, Blue, Green, Brown, Gold or Orange. The interior color is the buyer's own words, not a list Ridekick holds. Each connection can ask a limited number of times a day, and the answer says when a limit is reached. Any connected assistant can use it; it needs no extra permission and shows nothing about the buyer. If found is false, Ridekick lists no such make and model.

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": {
      "make": "<make>",
      "model": "<model>"
    },
    "name": "see_car_choices"
  }
}

Input Schema

NameRequiredDescriptionDefault
zipNoOptional. The buyer's five-digit ZIP code. With it and year, you get a yes or no for cars near the buyer.
fuelNoOptional, with zip. A fuel type to look for. A call with a ZIP code and no fuel can return the `fuels` listed near the buyer.
makeYesThe make, for example Honda.
trimNoOptional. Narrows the trims to this trim. With zip, a trim to look for.
yearNoOptional for the choices; required with zip. Narrows the trims to this model year.
modelYesThe model, for example Civic.
radiusNoOptional, with zip. Miles from the buyer's ZIP, from 1 to 100. The default is 100.
drivetrainNoOptional, with zip. A drivetrain to look for.
exteriorColorNoOptional, with zip. The exterior color: one of Black, White, Gray, Silver, Red, Blue, Green, Brown, Gold or Orange. A call that gives one color and not the other is refused.
interiorColorNoOptional, with zip. The buyer's own words for the interior color. A call that gives one color and not the other is refused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Beyond the readOnly/non-destructive annotations it discloses a lot: a daily per-connection rate limit with the answer signaling when it is reached, no extra permission or buyer data exposure, the fact that drivetrain and fuel lists come back empty without a ZIP code, the refusal rule for giving only one of the two colors, and that found=false means no such make and model exists. It also bounds the response carefully (no dollar amounts, colors, options, counts, dealership, town or distance) so the agent will not over-promise to a buyer. No contradictions with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The purpose is front-loaded and the flow ordering is sensible, but the body drifts into long run-on sentences that mix output semantics, rate limits, auth posture and color enumerations. Several points are repeated: 'no count' appears twice, and the disclaimer that the answer says nothing about availability is stated once for the choices and again, at greater length, for carsNearby. Tightening would preserve all the information in roughly half the text.

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 ten-parameter tool with no output schema and heavy conditional behavior, the definition covers enough to call it correctly: what the lists mean, when fields are empty, when the yes/no appears, and the found=false terminal case. The one real gap is `trimsYear`, referenced as though the agent should act on it but absent from the schema and unexplained. Everything else an agent needs to construct a valid call is present.

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?

Input coverage is 100%, so the schema already documents all ten parameters including the ZIP-plus-year dependency and the paired-color refusal. The description mostly restates these (the exterior color list and the interior-color-in-own-words rule are verbatim schema content) and adds only the interaction detail that fuel and drivetrain lists are empty without a ZIP. It also introduces `trimsYear`, which is not in the input schema, leaving the agent to guess whether it is an output field or a missing parameter.

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?

The opening sentence gives a specific verb and resource: it shows the model years and trim levels Ridekick lists for one make and model. It also sketches the secondary ZIP-based behavior and the SUV-style multi-call case, so an agent knows the tool is more than a plain lister. It never names the closest siblings (see_car_choices_options, see_cars_near_buyer) as the thing to use instead, so differentiation is by description rather than by routing.

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?

Explicit entry conditions are given: 'A new-car ask starts here: a buyer who asks for a new car of a make and model... and has named no listing', plus the kind-of-car case where each make/model is one call and needs no ZIP or model year. It also states what follows in the flow ('requests_preview follows it'). What is missing is a negative rule — when NOT to call this and which sibling to use instead, particularly for the nearby-listing case that overlaps with the see_cars_near_buyer family.

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