Skip to main content
Glama

RestaurantDoctorAI

Booking fee check

restaurantdoctor_booking_fees
Read-onlyIdempotent

Works out what a US restaurant's reservation app costs it, as the free booking fee check on restaurantdoctorai.com does: a month, a year, per guest who booked through it and as a share of the average spend, from the plan's published price (dated, sourced) or the owner's invoice, plus fees per guest and the percentage on deposits. Of the apps checked, only OpenTable charges per guest: for guests from its own app and website, possibly from Google and partners, and on Basic from the restaurant's own website. Returns a one-sentence headline first, the month line by line, what isn't counted, what the owner can do (book direct, mark no-shows, the contract's notice date), other apps' published prices as information, not a recommendation, the caveats and sources. It answers what OpenTable, Resy, Tock, Yelp, Toast Tables, SpotOn or SevenRooms costs a restaurant per reservation or per guest. It needs the app and plan (on the invoice) and, for OpenTable, last month's guests from its covers report by where they booked; the rest is optional. A figure that isn't sent is never counted as 0. Not affiliated with any app; it reads no account. The figures aren't stored; only an anonymous daily count of calculator runs is kept.

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": {
      "platform": "<platform>"
    },
    "name": "restaurantdoctor_booking_fees"
  }
}

Input Schema

NameRequiredDescriptionDefault
platformYesThe app and plan, on the invoice. tock_ = Tock, now sold by Resy; other = any app not listed, with monthlyFee.
firstMonthNo
monthlyFeeNo
renewalDateNo
averageSpendNo
networkCoversNo
partnerCoversNo
prepaidAmountNo
websiteCoversNo
networkCoverFeeNo
partnerCoverFeeNo
websiteFlatAddOnNo
prepaidFeePercentNo

Output Schema

NameRequiredDescriptionDefault
asOfYesThe day prices were read.
linkYesOpens the check with these figures.
nameYesThe plan.
yearYes
monthYesUS dollars, like every amount.
notesYes
resultYes
caveatsYes
feeFromYes
ofSpendYes
partialYesTrue when the headline says at least.
sourcesYes
headlineYesThe result in one sentence.
noticeByYes
perGuestYes
breakdownYesThe month.
freeCheckYes
workedOutYes
firstMonthYes
notCountedYes
alternativesYesOther apps' monthly prices: information, not a recommendation.
whatYouCanDoYes
ifBookedDirectYes
perNetworkGuestYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / headline / description
      Previous value: -"Show it first."New value: +"The result in one sentence."
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value beyond them: it is not affiliated with any app, reads no account, stores no figures, and keeps only an anonymous daily run count. It also discloses the output shape (one-sentence headline, month line by line, what isn't counted, caveats and sources) and that it is informational, not a recommendation.

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 and required inputs are front-loaded, which is good, but the body is a dense, comma-spliced run-on that mixes output format, caveats, coverage list, input requirements and privacy notes into a single block. Given the tool's complexity some length is justified, but the packing makes it harder to scan than it needs to be.

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?

An output schema exists, so return values need not be spelled out, yet the description still sketches them. Combined with the input requirements, the missing-value rule, the source/caveat disclosure and the privacy statement, an agent has enough to call this correctly for a 13-parameter calculator. The only shortfall is coverage of the less-common optional fee parameters.

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?

With 13 parameters and very low reported schema coverage, the description has to carry weight, and it does partially: it names platform as the required input, states that OpenTable needs last month's guests by booking source, that sevenrooms/other need monthlyFee, that the rest is optional, and that a missing figure is never treated as 0. It does not add per-field semantics for the remaining fields (renewalDate, prepaidAmount, prepaidFeePercent, the various fee overrides), leaving those to the schema.

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: it computes what a US restaurant's reservation app (OpenTable, Resy, Tock, Yelp, Toast Tables, SpotOn, SevenRooms) costs per month, per year, per guest and as a share of average spend. That scope is clearly distinct from siblings like restaurantdoctor_card_fees or restaurantdoctor_delivery_price, so an agent can route without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives the use context (reservation-app cost analysis, mirroring the free check on restaurantdoctorai.com) and lists which apps it answers for, which implies when to reach for it. But it never names an alternative tool or an explicit when-not condition, so selection against the other 20 restaurantdoctor tools is left to inference.

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