Sedna Genesis

booking_create

Destructive

Submits a request for a booking or a request for an option.

This action re-prices and submits the request. booking_detail_mod is a stateless preview: selections made there are not stored automatically. Therefore selected_extras MUST repeat every extra the customer selected, using the exact id_opt and quantity. Pass an empty list only when the customer selected no optional extras. Never report an extra as selected unless this tool's saved_extras verification confirms it.

Full client details (name, email, phone) are required to submit the request. **** strong rule: AI should not guess or input customer information on its own. It must ask customers to input it on its own.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`pax`	Yes	Number of passengers.
`mode`	No	The type of creation, 'booking' or 'option' (defaults to 'booking').	booking
`dateEnd`	Yes	The end date (DD/MM/YYYY).
`id_boat`	Yes	The unique boat identifier.
`id_tbf1`	Yes	The TBF1 identifier for the booking.
`dateStart`	Yes	The start date (DD/MM/YYYY).
`client_name`	Yes	The client's full name.
`client_email`	Yes	The client's valid email address.
`client_phone`	Yes	The client's contact phone number.
`selected_extras`	Yes	Required complete selection. Example: [{"id_opt": 123, "selected": true, "quantity": 1}]. Use [] only when no optional extra was selected.
`arrival_selected`	No
`currency_id_devise`	No
`departure_selected`	No
`arrival_port_pay_option`	No
`departure_port_pay_option`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 11, 2026

removedInput schema / properties / selected_extras / anyOf

Removed value: -[
-  {
-    "items": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / selected_extras / default
```
Removed value: -null
```

addedInput schema / properties / selected_extras / description

Added value: +"Required complete selection. Example:\n[{\"id_opt\": 123, \"selected\": true, \"quantity\": 1}].\nUse [] only when no optional extra was selected."

addedInput schema / properties / selected_extras / items

Added value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

addedInput schema / properties / selected_extras / type
```
Added value: +"array"
```

changedInput schema / required

Previous value: -[
-  "client_name",
-  "client_email",
-  "client_phone",
-  "id_tbf1",
-  "id_boat",
-  "dateStart",
-  "dateEnd",
-  "pax"
-]New value: +[
+  "client_name",
+  "client_email",
+  "client_phone",
+  "id_tbf1",
+  "id_boat",
+  "dateStart",
+  "dateEnd",
+  "pax",
+  "selected_extras"
+]

First observedSep 10, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description adds real behavioral context beyond them: the action re-prices before submitting, selections are not auto-persisted from the preview tool, and submitted extras must be verified via saved_extras. It does not cover auth requirements, error modes, or how the saved_extras verification is surfaced, so it stops short of 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-loads the core purpose in the first sentence and keeps each following sentence on a distinct, useful point (repricing, preview contrast, extras repetition, client data, no-guessing rule). Minor waste: leftover markdown backticks and the embedded '**** strong rule' formatting are noisy, but content is dense rather than padded.

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

Completeness3/5

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

For a 15-parameter, 9-required mutation with no output schema, the description covers the highest-risk pieces (extras fidelity, client data, submission semantics) but leaves the arrival/departure, currency, and port-pay parameters unexplained. An agent would have to infer those from terse schema text alone.

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 coverage is 67%, so the schema documents most parameters. The description adds meaningful semantics for selected_extras (must repeat every extra with exact id_opt and quantity, empty list only when nothing was selected) and for the client_* fields, but it says nothing about arrival_selected, departure_selected, currency_id_devise, arrival_port_pay_option, or departure_port_pay_option.

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 (submits) and resource (booking/option request) and explicitly contrasts this action with booking_detail_mod, which is called out as a stateless preview. An agent can distinguish this from siblings like booking_detail and booking_detail_mod 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 Guidelines5/5

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

Gives explicit routing conditions: use this to actually submit, use booking_detail_mod only to preview. It also states prerequisites (full client details required) and the strong rule that the AI must not invent customer data but must ask the customer — a clear when/when-not instruction.

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

All Sedna Genesis 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?