Personalized Gifts Delivered

Create a draft order

create_draft_order

Saves a draft of the order (the logo from check_logo, the card message, the sign-off, the occasion and the kind of gift) and returns a private link. The customer opens the link to check the preview and every card, add their recipient list and pay on the website. Takes no recipient names or addresses and no payment details. Each call saves a new draft with its own link. The answer says when the link expires.

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": {
      "mode": "<mode>",
      "card_message": "<card_message>",
      "signed_by": "<signed_by>",
      "occasion": "<occasion>"
    },
    "name": "create_draft_order"
  }
}

Input Schema

Name	Required	Description
`mode`	Yes	business for a company logo, personal for a personal gift.
`boxes`	No	Optional estimate of how many boxes; the recipient list sets the real count.
`logo_ref`	No	From check_logo. Leave it out and the customer adds the logo on the website.
`occasion`	Yes	The occasion, as get_gift_box_details names them.
`signed_by`	Yes	Who the cards are from, printed under the message.
`card_message`	Yes	The message printed on every card. get_gift_box_details gives the rules.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only say readOnly=false, idempotent=false, openWorld=true; the description adds that every call creates a fresh draft with its own link (concrete consequence of non-idempotency), that the link is private and time-limited, and that the response states the expiry. That is real behavioral context an agent cannot get from the annotation flags.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with what is saved and what comes back, then the usage boundary, then the repeat-call and expiry behavior. No filler and no restatement of the title.

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?

There is no output schema, yet the description still tells the agent what the response contains (a private link and its expiry). Combined with the flow explanation and the explicit exclusions, nothing needed to call this correctly is missing.

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 baseline would be 3, but the description adds negative-space guidance absent from the schema — no recipient names, addresses or payment details belong in the call — and explains that the draft is optional-input tolerant (logo may be added later on the website). It also ties occasion and card_message to the naming/rules given by get_gift_box_details.

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?

Specific verb and resource ('Saves a draft of the order') plus an explicit return value ('returns a private link'). It also enumerates what is captured (logo, card message, sign-off, occasion, gift kind), which distinguishes it from siblings like quote_gift_boxes or get_order_status without needing their schemas.

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?

Clear about the situation this is for: producing a link the customer uses to preview cards, add a recipient list and pay. It also draws a hard boundary ('takes no recipient names or addresses and no payment details'), pointing that work at the website. It does not explicitly contrast with quote_gift_boxes, so no named alternative is given for pricing-only flows.

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

All Personalized Gifts Delivered 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?