Bay Area SUV fare estimates, tentative availability and booking links for airport and hourly rides.
Scored across 2 tools
Each tool serves a distinct purpose: one checks ride availability, the other provides a price quote. Despite sharing input parameters, their actions are clearly separated and unambiguous.
Both tools follow a consistent verb_noun pattern: check_ride_availability and quote_ride. The naming is predictable and aligns well with their functions.
With only two tools, the server feels thin for a ride service, though both are essential for the stated quote/availability workflow. The count is borderline but not extreme.
The server covers the core pre-booking steps (availability and pricing), but booking is deliberately left to an external URL. This is a minor gap given the server's focus on quotes, so it's moderately complete.
Check a requested Bay Area SUV pickup time against current scheduling constraints. Supply the same route, pickup time and passenger inputs as quote_ride. Returns only available, unavailable, or unknown. An available result is tentative and is not a hold or reservation; complete the request at https://www.blackcarservice.co/book. Hourly rides require hours (1–24); other ride types omit hours.
| Name | Required | Description | Default |
|---|---|---|---|
| hours | No | Required for hourly service; omit for airport and one-way rides. Billed minimums apply. | |
| pickup_at | Yes | ISO 8601 timestamp with explicit UTC offset. Clarify the customer's pickup time in America/Los_Angeles; account for daylight saving time. | |
| trip_type | Yes | ||
| passengers | Yes | ||
| pickup_address | Yes | Full pickup street address or airport, including city and state. | |
| dropoff_address | Yes | Full destination. For hourly service returning to pickup, repeat the pickup address. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide openWorldHint=true but readOnlyHint=false; the description adds key behavioral context by stating 'An available result is tentative and is not a hold or reservation' and that it 'Returns only available, unavailable, or unknown.' This clarifies the non-committal nature of the result, going beyond the annotation flags. No contradiction with annotations is present.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a compact two-sentence paragraph, front-loaded with the primary purpose and including the booking URL as a call-to-action. Every sentence contributes value: purpose, input consistency, output behavior, and parameter rule. No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description explicitly states the return set: 'Returns only available, unavailable, or unknown.' It also clarifies the tentative nature of availability and the hours condition. For a simple check tool with a clear sibling reference, this is adequate; minor gaps like error handling are not critical.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the 'hours' parameter with 'Required for hourly service; omit for airport and one-way rides.' The description repeats this ('Hourly rides require hours (1–24); other ride types omit hours') without adding new semantic detail. With 67% schema coverage, the description provides minimal additional meaning beyond what the schema already conveys.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Check a requested Bay Area SUV pickup time against current scheduling constraints.' It also differentiates from the sibling quote_ride by stating 'Supply the same route, pickup time and passenger inputs as quote_ride,' clarifying the tool's distinct purpose (checking availability vs. quoting).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states the tool uses the same inputs as quote_ride and gives a conditional rule for the 'hours' parameter ('Hourly rides require hours (1–24); other ride types omit hours'). It implies this tool is for checking availability and directs completion at the booking URL, but it does not explicitly state when to use this instead of quote_ride, leaving some inference to the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Estimate Black Car Service SUV fares in the San Francisco Bay Area for SFO, OAK and SJC airport transfers, point-to-point rides and hourly chauffeur service, for 1–7 passengers. Pickup dates begin tomorrow in America/Los_Angeles. Hourly rides require hours (1–24); other ride types omit hours. The price excludes extras and gratuity. No availability check, hold, reservation, or payment is performed.
| Name | Required | Description | Default |
|---|---|---|---|
| hours | No | Required for hourly service; omit for airport and one-way rides. Billed minimums apply. | |
| pickup_at | Yes | ISO 8601 timestamp with explicit UTC offset. Clarify the customer's pickup time in America/Los_Angeles; account for daylight saving time. | |
| trip_type | Yes | ||
| passengers | Yes | ||
| pickup_address | Yes | Full pickup street address or airport, including city and state. | |
| dropoff_address | Yes | Full destination. For hourly service returning to pickup, repeat the pickup address. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description discloses important behavioral facts: pickup dates start the next day in America/Los_Angeles, hourly rides require hours, the price excludes extras and gratuity, and no hold/reservation/payment is performed. This gives the agent a clear safety and side-effect picture without contradicting 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four dense sentences front-load the core purpose and then layer constraints and exclusions. Every sentence earns its place, and there is no redundant or promotional language.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is complete enough to correctly select and invoke the tool: it covers scope, required inputs, conditional parameter behavior, and explicit non-actions. It does not describe the response shape, but the tool name and 'Estimate fares' language make the return intent clear, and no output schema is provided.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 67%, so the description does not need to carry every parameter, and it adds value by tying trip_type to airport transfers, point-to-point, and hourly service, and by restating the 1–7 passenger range. It slightly overlaps with schema descriptions for hours and pickup_at, but the ride-type mapping is genuinely additive.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Estimate') and resource ('Black Car Service SUV fares') and scopes it precisely to Bay Area airports, point-to-point rides, and hourly service. It also differentiates itself from check_ride_availability by explicitly stating that no availability check is performed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives clear when-to-use context for SFO/OAK/SJC transfers, point-to-point, and hourly service, plus an explicit 'no availability check' exclusion that routes away from the sibling tool. It also clarifies the conditional hours parameter and the pickup-date constraint.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_ride_availabilityquote_ridePrivate chauffeured transport in Los Angeles. Price any trip at a fixed all-in rate, no account.
Real-time passenger van rental availability and pricing across major US cities.
California's published auto insurance averages. Not a quote; we are not licensed here yet.
Public chauffeur prices, policy and consent-led offers for travel bookers and AI assistants.
Add one secure layer between your agents and this server.
