Skip to main content
Glama

Recommend rental

recommend_rental
Read-onlyIdempotent

ONE call for a car-hire question at one airport: the usual total for the person's dates split into rental, second-driver fee, cover and out-of-hours fee (deposit shown separately as a card hold), the suppliers that usually suit their needs with each requirement marked meets / unverified and its evidence (debit card, deposit limit, automatic, 7 seats, car size, cross-border - checked together, company by company), and the correctly dated search link to book. Measured history, not live offers. Use first when the person gives dates or needs (debit card, deposit limit, second driver, late arrival).

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": {
      "airport": "<airport>"
    },
    "name": "recommend_rental"
  }
}

Input Schema

NameRequiredDescriptionDefault
ageNoMain driver's age in years (default 35). Under 25 or over 70 often costs more.
airportYesAirport id, IATA code or name, e.g. 'faro', 'FAO', 'Faro Airport'
car_typeNoCar size; omit for every size.
currencyNoEUR, GBP, USD...
automaticNoTrue for automatic gearbox only.
residenceNoTwo-letter country of residence, e.g. GB
debit_cardNoTrue if the driver has no credit card - only cars whose desk takes a debit card for the deposit.
full_coverNoTrue if they want DiscoverCars' Full Coverage priced in.
max_depositNoThe most the person can have held as a deposit (0 = no deposit). A hard limit, checked supplier by supplier.
pickup_dateNoYYYY-MM-DD
pickup_timeNoHH:MM
cross_borderNoTrue if they will drive into another country.
dropoff_dateNoYYYY-MM-DD
dropoff_timeNoHH:MM
extra_driverNoTrue if a second driver will drive - their fee is then in every total.
seven_seaterNoTrue if they need 7 or more seats.
dropoff_airportNoOptional return airport (code or name) when it differs from the pick-up - a one-way hire. One-way fees are not measured: the live search shows them in each total

Output Schema

NameRequiredDescriptionDefault
noteNo
errorNo
queryNo
marketNo
airportNo
depositNo
currencyNo
data_typeNo
provenanceNo
report_urlNo
cost_estimateNo
booking_searchNo
suppliers_usually_bestNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / dropoff_airport
      Added value: +{
      +  "description": "Optional return airport (code or name) when it differs from the pick-up - a one-way hire. One-way fees are not measured: the live search shows them in each total",
      +  "type": "string"
      +}
  2. Changed3 schema fields changed
    • addedInput schema / properties / car_type
      Added value: +{
      +  "description": "Car size; omit for every size.",
      +  "enum": [
      +    "small",
      +    "medium",
      +    "large",
      +    "suv",
      +    "estate",
      +    "vans",
      +    "premium"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / cross_border
      Added value: +{
      +  "description": "True if they will drive into another country.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / seven_seater
      Added value: +{
      +  "description": "True if they need 7 or more seats.",
      +  "type": "boolean"
      +}
  3. Changed1 schema field changed
    • addedOutput schema / properties / report_url
      Added value: +{
      +  "type": "string"
      +}
  4. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description's genuinely additive disclosure is "Measured history, not live offers" plus the note that the deposit is a card hold shown separately, which prevents the agent from presenting stale figures as bookable prices. It says nothing about latency, coverage limits, or what happens when no supplier meets the requirements.

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?

It is front-loaded correctly with the highest-value claim ("ONE call" for the whole question), but the middle is a single unbroken run-on sentence dense with parenthetical clauses that are hard to parse on a first read. The output inventory consumes most of the length even though an output schema is supplied.

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 17 parameters, an output schema and full annotation coverage, the description supplies the caveats an agent most needs: results are historical rather than live, the deposit is a hold, and one-way fees are excluded from measured totals. Given the output schema exists it need not explain return shapes, though the space spent doing so crowds out guidance on interpreting unsatisfied requirements.

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 each of the 17 parameters is already documented in the schema, which sets the baseline at 3. The description adds only the framing that requirements are "checked together, company by company" and that the breakdown includes rental, second-driver fee, cover and out-of-hours fee — semantics about the evaluation, not new meaning for individual parameters.

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 clause names a specific verb and resource — "ONE call for a car-hire question at one airport" — and the body enumerates exactly what comes back (usual total split, supplier matches with requirement flags, dated search link). It never names a sibling to contrast with, so the agent must infer that build_search_link and supplier_terms are downstream steps rather than substitutes.

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?

"Use first when the person gives dates or needs (debit card, deposit limit, second driver, late arrival)" gives concrete entry triggers and implies ordering relative to siblings. It stops short of stating when NOT to call it — e.g. price-only comparisons across airports, which is where compare_airports would apply.

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.