Skip to main content
Glama

Create a delivery

create_delivery
Destructive

Books a delivery. Pass quote_id from get_quote, or pickup+dropoffs directly. fund=true (default) holds the price from your wallet and starts dispatch. Use dryRun=true first to see the price without committing. Returns next_action. The delivery card shows these details: reply in one short line instead of repeating them.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_delivery"
  }
}

Input Schema

NameRequiredDescriptionDefault
fundNo
itemsNo
speedNo
dryRunNo
pickupNo
serviceNo
urgencyNo
dropoffsNo
metadataNo
quote_idNo
contingencyNo
webhook_urlNo
external_refNo
instructionsNo
scheduled_atNo
workspace_idNo
vehicle_classNo
idempotency_keyNo
dispatch_timeout_hoursNoSearch duration in hours, 0.25–72. Default ASAP 24h, otherwise 72h; pickup windows and today deadlines still apply. No repeated funding.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds the consequence the agent actually needs: fund=true 'holds the price from your wallet and starts dispatch,' making the financial effect explicit, and dryRun previews pricing without committing. It also notes the return of next_action. It doesn't mention the idempotency_key or whether a funded booking can be cancelled/reversed, which keeps it at 4.

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, then the quote-vs-manual choice, then the money/dryRun semantics – a sensible decision-first ordering with little waste. The closing line about the delivery card is a formatting instruction to the agent rather than tool semantics, but it is brief.

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 19-parameter, deeply nested booking tool with no output schema and real wallet charges, the description covers the critical invocation path but omits the meaning of most fields and does not explain what values next_action can take. Adequate to call it safely in dry-run, but not sufficient to configure a complex multi-dropoff booking.

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

Parameters2/5

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

Schema description coverage is only 5% across 19 parameters, so the description must carry the load. It explains just three: quote_id (source from get_quote), the pickup/dropoffs alternative, and fund/dryRun. The nesting-heavy items array, speed/service/urgency enums, contingency, scheduled_at, webhook_url, and vehicle_class are left entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Books a delivery') and immediately distinguishes the two booking modes: quote_id from get_quote vs. ad-hoc pickup+dropoffs. It doesn't differentiate from sibling creation tools like create_batch or create_store_pickup, so it stops short of a 5.

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

Usage Guidelines4/5

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

Gives a clear recommended workflow: pass quote_id from get_quote or supply pickup+dropoffs, and 'Use dryRun=true first to see the price without committing.' The default behavior of fund=true is also stated. It lacks explicit when-not guidance (e.g., when to use create_batch or create_return instead), so it's strong but not exhaustive.

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.