Zovo Tip Pool Calculator

Calculate tip-out

calculate_tip_out

Read-onlyIdempotent

Use this when the user wants a tip out calculator: servers or bartenders tip out a percent of their sales or tips to support staff (bussers, bartenders, hosts, food runners, barbacks). Takes each server's sales and/or tips and the tip-out rules (e.g. busser 3% of sales, bar 1.5% of sales), plus optional support staff with roles and hours. Returns each server's tip-out per role (rounded to the cent), what each server keeps, each support person's share by hours with largest-remainder rounding so it adds up to what was tipped out, warnings, and a printable PDF tip-out sheet with signature lines plus a CSV. Does not give legal advice, compute wages or taxes, or connect to a POS. Do not use for a shared pool split by hours (use calculate_tip_pool) or for a bill split among diners.

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": {
      "servers": "<servers>",
      "tip_outs": "<tip_outs>"
    },
    "name": "calculate_tip_out"
  }
}

Input Schema

Name	Required	Description
`label`	No	Optional title for the tip-out sheet, e.g. "Saturday dinner".
`servers`	Yes	Servers or bartenders who tip out, each with sales and/or tips. Array of {name, sales, tips}, or pasted lines, e.g. [{"name":"Ana","sales":1850,"tips":340}] or "Ana sales 1850 tips 340\nBen sales 1420 tips 260".
`currency`	No	ISO currency code, default USD, e.g. EUR.
`tip_outs`	Yes	Who gets what share, e.g. "busser 3% of sales, bartender 1.5% of sales, host 1% of sales" or [{"role":"busser","percent":3,"basis":"sales"}]. A plain 3 or "3%" means 3% to the support staff as one group.
`support_staff`	No	Optional people receiving the tip-out, with role and hours, e.g. [{"name":"Kim","role":"busser","hours":6}]. Each role's tip-out is split among its people by hours (equal if no hours).
`tip_out_basis`	No	"sales" or "tips": what a percent without "of sales" or "of tips" is taken from. Default: sales when every server has sales, else tips.

Output Schema

Name	Required	Description	Default
`note`	Yes
`label`	Yes
`totals`	Yes
`servers`	Yes
`currency`	Yes
`tip_outs`	Yes
`warnings`	Yes
`downloads`	Yes
`unassigned`	Yes
`assumptions`	Yes
`explanation`	Yes
`support_staff`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed-world), so the description is not needed to establish that this is a safe read. It does add real behavioral context: per-role rounding to the cent, largest-remainder allocation so support shares sum exactly to the pool, and emission of warnings. Some of the return-value enumeration (PDF sheet with signature lines, CSV) overlaps with the output schema, which keeps this just below a 5.

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?

Front-loaded with the trigger condition, then the input shape, then outputs, then scope limits — a logical order with no filler sentences. It runs long and repeats some return-value detail already captured by the output schema, which keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter, nested-input calculation tool, the description covers inputs, rounding behavior, outputs, and explicit out-of-scope cases (legal advice, wages/taxes, POS integration). An agent has enough to decide to call it and to explain the result to a user.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description goes further by giving a concrete rule-of-thumb example for tip_outs ("busser 3% of sales, bar 1.5% of sales") and clarifying that a bare 3 or "3%" means the support staff as a single group — a semantic distinction the schema hint only partly covers. It also explains how support_staff hours drive the per-role split, adding meaning beyond the field-level descriptions.

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?

Names a specific operation (tip-out calculation) and domain (servers/bartenders tipping out a percent of sales or tips to support staff), and enumerates the roles involved. It also explicitly distinguishes itself from siblings by naming calculate_tip_pool for hourly pool splits, so the agent can route without opening the schemas.

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?

Opens with a direct trigger condition ("Use this when the user wants a tip out calculator") and closes with two explicit exclusions plus the correct alternative for one of them (calculate_tip_pool) and the boundary for bill splitting. When-to-use, when-not-to-use, and the alternative are all present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Zovo Tip Pool Calculator tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?