warp-agent-mcp

Batch Book Shipments

batch_book

Destructive

Book MANY already-quoted lanes in ONE call (sequential, one card charge per row). Use this after batch_quote when the user says "book all of them" or "book rows 1, 3, 5" — do NOT call book in a loop. Each row needs a quote_id (the same one batch_quote returned for that row). Pickup/delivery default to the shared addresses at the top level so a single warehouse → many destinations only needs one address pair. Returns a progress card showing per-row Booked/Failed status with tracking numbers.

Input Schema

TableJSON Schema

Name	Required	Description
`bookings`	Yes	Array of bookings to confirm (1-25). Each is one freight shipment, one card charge.
`shared_notes`	No	Notes applied to every row without their own.
`shared_pickup`	No	Pickup address applied to every row that doesn't supply its own (FBA case: one warehouse → many destinations).
`shared_delivery`	No	Delivery address (all fields incl. contact phone and email) applied to every row that doesn't supply its own. Uncommon (usually each row goes somewhere different).
`shared_reference`	No	Reference applied to every row without its own.
`shared_accessorials`	No
`shared_pickup_window`	No
`shared_delivery_window`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 28, 2026

changedInput schema / properties / bookings / items / properties / delivery / description

Previous value: -"Per-row delivery. Omit to inherit from shared_delivery."New value: +"Per-row delivery (all fields incl. contact phone and email). Omit to inherit from shared_delivery; one of the two is required."

addedInput schema / properties / bookings / items / properties / delivery / properties / email / description
```
Added value: +"Delivery contact email. Required by Warp on every booking."
```

changedInput schema / properties / bookings / items / properties / delivery / required

Previous value: -[
-  "zipCode",
-  "city",
-  "state",
-  "street",
-  "contactName",
-  "phone"
-]New value: +[
+  "zipCode",
+  "city",
+  "state",
+  "street",
+  "contactName",
+  "phone",
+  "email"
+]

changedInput schema / properties / shared_delivery / description

Previous value: -"Delivery address applied to every row that doesn't supply its own. Uncommon (usually each row goes somewhere different)."New value: +"Delivery address (all fields incl. contact phone and email) applied to every row that doesn't supply its own. Uncommon (usually each row goes somewhere different)."

addedInput schema / properties / shared_delivery / properties / email / description
```
Added value: +"Delivery contact email. Required by Warp on every booking."
```

changedInput schema / properties / shared_delivery / required

Previous value: -[
-  "zipCode",
-  "city",
-  "state",
-  "street",
-  "contactName",
-  "phone"
-]New value: +[
+  "zipCode",
+  "city",
+  "state",
+  "street",
+  "contactName",
+  "phone",
+  "email"
+]

Changed4 schema fields changedSep 11, 2026
- addedInput schema / properties / bookings / items / properties / delivery / properties / zipCode / pattern
```
Added value: +"^\\d{5}$"
```
- addedInput schema / properties / bookings / items / properties / pickup / properties / zipCode / pattern
```
Added value: +"^\\d{5}$"
```
- addedInput schema / properties / shared_delivery / properties / zipCode / pattern
```
Added value: +"^\\d{5}$"
```
- addedInput schema / properties / shared_pickup / properties / zipCode / pattern
```
Added value: +"^\\d{5}$"
```
First observedJul 30, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations only carry destructiveHint=true, so the description adds real value: sequential execution, one card charge per row, per-row Booked/Failed outcome, and the session-scoped quote_id expiry warning. It stops short of stating what happens to already-charged rows if a later row fails, or any refund/permission detail, so it is strong but not exhaustive.

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?

Four sentences, front-loaded with the core action and followed by the routing rule, the required key, the address-inheritance shortcut, and the return shape. Dense and mostly waste-free, though the address-inheritance sentence runs long relative to its informational payload.

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 destructive 8-param batch mutation with no output schema, the description covers the return value (progress card with per-row status and tracking), the batching contract, and the inheritance defaults. Remaining gaps are edge-case failure/refund semantics, which are secondary but not covered by any structured field.

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?

With schema coverage at 63%, the description compensates by explaining the shared_* inheritance model (per-row values fall back to top-level shared values) and the warehouse → many destinations case. The quote_id session constraint and row-count economics are also surfaced. It does not add format detail for windows or accessorials, which the schema leaves bare.

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 (book), resource (already-quoted lanes), and scope (MANY in ONE call), and explicitly distinguishes itself from the sibling `book` by forbidding the loop pattern. An agent can route between batch_book, book, and batch_quote 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?

Names the trigger conditions verbatim ('book all of them', 'book rows 1, 3, 5'), the required prerequisite (after batch_quote, using the same quote_id), and the explicit anti-pattern (do NOT call book in a loop). This is textbook when/when-not/alternative guidance.

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

All warp-agent-mcp 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.

Batch Book Shipments

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources