Ménage Parfait

Cancel a booking (free, at least 48 h before; customer confirms by email code)

cancel_booking

Destructive

Cancels an existing home-cleaning booking free of charge when the visit is at least 48 hours away (terms, article 7.4). Two calls: 1) without verification_code - checks the request and emails a 6-digit code to the address on the booking; 2) ask the customer for the code and call again with the same arguments plus verification_code. Recurring plans: scope "visit" cancels one visit (with visit_date), scope "plan" stops all upcoming visits (visits less than 48 hours away stay scheduled). Less than 48 hours before, or for an already-paid booking: use send_message or call 01 89 19 68 69.

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": {
      "booking_reference": "<booking_reference>",
      "email": "<email>"
    },
    "name": "cancel_booking"
  }
}

Input Schema

Name	Required	Description	Default
`email`	Yes	Email address used for the booking
`scope`	No	booking = one-off booking (default); visit = one visit of a recurring plan; plan = stop the recurring plan
`language`	No	Language of the emails	fr
`agent_name`	No	Name of the assistant/app
`visit_date`	No	With scope=visit: date of the visit to cancel
`booking_reference`	Yes	Booking reference given at booking (booking_reference)
`verification_code`	No	6-digit code from the email, second call only

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the destructiveHint/openWorldHint annotations: it discloses that cancellation is free, the 48-hour eligibility window, the email-code confirmation round trip, and that scope=plan leaves visits under 48 hours scheduled. No contradiction with destructiveHint=true.

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 core action and eligibility rule, then the procedural flow, then edge cases. Dense but mostly earns its space; the article 7.4 citation is minor filler.

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?

For a 7-parameter, no-output-schema, destructive tool, the description covers eligibility, the confirmation protocol, scope semantics, and fallbacks. It could say more about what the first call returns or what happens on an invalid/expired code.

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 the baseline is 3, but the description adds real meaning: how scope interacts with visit_date, and the asymmetric behavior of plan cancellation that preserves near-term visits. verification_code usage (second call only) is reinforced in prose.

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 (cancels a home-cleaning booking) plus the key qualifying conditions (free, at least 48 hours out). It is clearly distinguishable from siblings like reschedule_booking and create_booking without opening any schema.

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?

Explicitly prescribes the two-call verification flow, explains what to do between calls, and names alternatives for the excluded cases (send_message or phone when under 48 h or already paid). Scope selection guidance for recurring plans is also spelled out.

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

All Ménage Parfait 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?