Skip to main content
Glama

Trade-in position

trade_in_position
Read-onlyIdempotent

Sizes up a trade-in from written offers (CarMax, Carvana, dealers) and what's still owed: the best offer still open, which is the floor a dealer's trade number is compared with, the equity or negative equity, and, with a state and vehicle price, the sales tax the trade saves where the state credits it. Use it before visiting dealers; check_quote compares a quote's trade allowance with these offers.

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": {
      "offers": "<offers>"
    },
    "name": "trade_in_position"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity or county in the state's rate table (23 states; state_rules says which), like Pittsburgh or Allegheny County: sets the combined rate from the state's own rate file. Where a city is in several counties (Chicago, Milwaukee), give county too. A place name only, never an address or ZIP
stateNoTwo-letter state code, for the tax the trade saves
countyNoCounty from the state's list (Pennsylvania, Nevada, Wisconsin; state_rules lists them), like Allegheny County: sets the combined rate. A county name only, never an address or ZIP
offersYesWritten trade-in offers, each with who made it, the amount and its last day
payoffNoWhat is still owed on the car being traded
doc_feeNoDoc fee; leave out to assume the state's cap, or a typical $450 where there is none
tax_rateNoCombined sales tax rate as a decimal, local tax included (0.07 for 7%); leave out to use the state's rate
vehicle_priceNoThe price of the car being bought, for the tax the trade saves

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / offers / description
      Added value: +"Written trade-in offers, each with who made it, the amount and its last day"
    • changedInput schema / properties / payoff / description
      Previous value: -"What is still owed on the car"New value: +"What is still owed on the car being traded"
    • changedInput schema / properties / state / description
      Previous value: -"Two-letter state code (DC included), like PA"New value: +"Two-letter state code, for the tax the trade saves"
    • changedInput schema / properties / vehicle_price / description
      Previous value: -"The new vehicle price, for the tax the trade saves"New value: +"The price of the car being bought, for the tax the trade saves"
  2. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description adds genuine analytical context – only open offers count, tax credit applies only in crediting states – but says nothing about error behavior when offers are sparse or how the tax/equity results are returned.

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 outputs are front-loaded in the first clause and the sibling routing comes last, which is the right order. The opening sentence is long and clause-heavy, but each clause names a distinct computed value, so little could be cut without losing semantic content.

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?

With 8 parameters at full schema coverage and no output schema, the description carries the burden of explaining what comes back, and it does so by naming the four result categories. What remains unstated is the result shape and how edge cases (expired offers, no payoff, no state given) are reported.

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 100%, so 3 is the baseline. The description goes beyond it by explaining the conditional coupling of parameters: 'with a state and vehicle price, the sales tax the trade saves' clarifies that the tax output only materializes when those two are supplied, and that the best offer is the comparison floor for dealer trade numbers.

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+resource ('sizes up a trade-in') and then enumerates exactly what it computes: best open offer, dealer-trade floor, equity/negative equity, and tax savings where the state credits it. This is clearly distinguishable from sibling quote-comparison and payment 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?

Gives explicit timing ('Use it before visiting dealers') and names the alternative with its different job ('check_quote compares a quote's trade allowance with these offers'). The agent knows both when to call this and where to route instead.

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