giftroam

Create a checkout link

create_checkout

Idempotent

Create a signed, single-purpose checkout link (30-minute expiry) for one gift to one country. The schema has no recipient fields on purpose: name, address, phone, delivery details and payment are collected on the secure page. Show the returned summary and get the user's explicit confirmation before sharing the link. Use the same idempotency_key when retrying.

Input Schema

TableJSON Schema

Name	Required	Description
`locale`	No	Language of the conversation with the user (e.g. he-IL, fr-FR). Localizes content and messages; prices and availability are unaffected. The checkout page opens in this language.
`country`	Yes	Destination country, ISO-3166 alpha-2.
`gift_id`	Yes	gift_id from search_gifts.
`quantity`	No	Always 1 in v1.
`delivery_date`	No	Requested delivery date YYYY-MM-DD; omit for as-soon-as-possible.
`gift_card_text`	No	Card message (≤180 chars) if the user already gave one.
`idempotency_key`	Yes	Client-generated key; retries with the same key return the same link.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present only when the call failed
`locale`	No	BCP-47 locale the texts are localized to
`summary`	No
`expires_at`	No
`checkout_url`	No	Single-purpose secure checkout link on checkout.giftroam.com (30-minute expiry)
`display_text`	No	Human-readable one-line summary of the result

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations, the description adds meaningful behavioral detail: the link is time-limited, single-purpose, scoped to one gift and one country, and intentionally collects recipient and payment details on the secure page. It also instructs the agent to confirm with the user before sharing, which is important safety-relevant behavior.

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?

The description is compact and front-loaded: the defining purpose appears first, followed by the most decision-relevant constraints and safety instruction. Every sentence earns its place, with no redundant or filler content.

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?

For a tool with a complete output schema and rich annotations, the description is sufficient. It covers what the link is, how it behaves, how to safely use it in conversation, and how to retry correctly. No essential operational context 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?

The schema already documents all 7 parameters with 100% coverage, so the baseline is 3. The description adds extra value by explaining why recipient fields are absent, clarifying the meaning of the idempotency_key behavior when retrying, and framing the gift_id/country scope.

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?

The description states a specific verb and resource: creates a signed, single-purpose checkout link for one gift to one country, with a 30-minute expiry. This is clearly distinct from the sibling tools, which are all read/query tools.

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?

The description gives clear operational guidance: show the returned summary and get explicit user confirmation before sharing the link, and reuse the idempotency_key on retries. It does not explicitly name alternatives or exclusion conditions, but the sibling tools are obviously different in function, so the context is clear enough.

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

All giftroam tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation4/5

Each tool targets a distinct resource/action: searching gifts, checking delivery, creating checkout, fetching details, looking up order status, and listing orders are all conceptually separate. Minor potential confusion exists between check_delivery and get_gift_details since both surface delivery-window information, but their primary purposes differ clearly.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: check_, create_, get_, list_, search_. The naming style is uniform and predictable, making it easy to infer each tool's function.

Tool Count5/5

Six tools is a well-scoped set for a gift-delivery e-commerce server. Each tool represents a meaningful step in the customer journey from search and eligibility to checkout and order tracking, without unnecessary redundancy.

Completeness4/5

The tool surface covers the core lifecycle: search, view details, check delivery, create checkout, list orders, and check order status. Minor gaps exist such as no explicit cancellation, returns, or order modification tools, but the publicly-facing purchase journey appears complete for the stated purpose.

Resources

Need Help?