Skip to main content
Glama

SMKlog Parcel Shipping Rates

Create a payment session for a shipping label

create_checkout_link

Turns a decided shipment into a payment session for buying its shipping label: the checkout amount and a handoff URL that opens SMKlog checkout prefilled with the parcel. Use it after get_parcel_quote, passing the quote_id that call returned, so the price is reused and no second carrier call is spent. Without a quote_id it prices the shipment live from the fields. The result carries a session_id: keep it, and get_checkout_status tells you when the human has paid and when the label exists.

Side effects: it writes a session record (30-day life, readable through get_checkout_status) and is not idempotent. Calling it twice makes two sessions and, without a quote_id, spends two carrier calls. It never charges: no card is touched and nothing is reserved until the human confirms the contents certification and the carrier-adjustment consent on the page and pays there. A stale link simply reprices.

No session is returned when a person has to price the shipment: freight, oversize, a quantity above 1, or an installed lithium battery crossing a border. Quote first to learn which case applies.

Parameter rules:

  • A valid quote_id overrides product, from_zip, to_zip, to_country and quantity. service is still honored.

  • An expired quote_id falls back to live pricing from the fields. If those were omitted too, the call fails with missing_required_fields, so pass them alongside an old id.

  • service is matched as a case-insensitive fragment of the display name ("Ground Advantage", "UPS Ground Saver"). A fragment that matches nothing silently anchors the cheapest rate, so read the service field in the result.

  • from_zip is a real 5-digit US ZIP. to_zip follows to_country (US, CA, GB, DE or AU).

  • On the four international lanes the human completes the customs declaration on the page, and duty is billed to the recipient on arrival.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
to_zipNoDestination postal code: a 5-digit ZIP for the US, or the destination country's own postal code. Required unless quote_id is given.
productNoPlain-words item description. Required unless quote_id is given.
serviceNoService to anchor the amount to, e.g. "USPS Ground Advantage". Cheapest when omitted; the human can still pick any service on the page.
from_zipNoOrigin US ZIP code, 5 digits. Required unless quote_id is given.
quantityNoIdentical parcels in this shipment. Default 1.
quote_idNoThe quote_id returned by a previous get_parcel_quote call. Valid for 15 minutes.
to_countryNoTwo-letter destination country: US (default), CA, GB, DE, AU.US

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoStanding caveats: live quote, human confirms consents and pays
amountYesLive-quoted checkout total for the anchored service, USD
intentYesAlways "session" — this tool never charges
methodNoPayment rails behind the checkout, e.g. stripe, card
serviceNoThe service the amount is anchored to
currencyYesISO currency, USD
session_idNoHandle for get_checkout_status, shaped as_ plus a UUID, good for 30 days. Null only when the session record could not be stored.
handoff_urlYesOpens the SMKlog checkout prefilled with this shipment
quote_reusedNoTrue when the amount came from a quote_id you supplied, so no carrier call was spent. False when this tool priced the shipment live -- either because no quote_id was given, or because the one given had expired.
identified_product_titleNoWhat the estimator understood the item to be

TDQS

A5/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important behavior: it writes a session record with a 30-day life, is not idempotent, never charges, and does not reserve funds until the human confirms on the page. It also explains stale-link repricing and the fallback from an expired quote_id, going well beyond what the annotations alone provide.

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 long but every section earns its place: purpose is front-loaded, side effects are clearly labeled, and parameter rules are grouped readably. The detail is necessary for a tool with 7 parameters and complex override/fallback behavior, so this is appropriate density rather than bloat.

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?

Given the output schema exists and the annotations are present, the description covers the remaining context comprehensively: lifecycle of the session, result fields to keep, side effects, no-session cases, international customs behavior, and parameter override rules. Nothing critical is missing for an agent to invoke this tool correctly.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds substantial semantic value: quote_id overrides product/from_zip/to_zip/to_country/quantity while still honoring service; expired quote_ids fall back to live pricing; service matching is case-insensitive and fragment-based; and from_zip must be a real 5-digit US ZIP. These rules are not present in the schema descriptions.

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: it turns a decided shipment into a payment session for buying a shipping label, producing an amount and a handoff URL prefilled with the parcel. It also clearly positions itself relative to its siblings by saying it is used after get_parcel_quote and that get_checkout_status tracks payment/label existence.

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?

The description gives explicit usage direction: use it after get_parcel_quote with the returned quote_id, and explains the consequence of omitting quote_id. It also lists when no session is returned (freight, oversize, quantity > 1, certain lithium batteries) and advises quoting first, which is clear when-to-use and when-not-to-use guidance.

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.

TDQS

A4.9/5.0
Disambiguation5/5

Each tool targets a distinct operation: live quote versus checkout session versus reference index versus tracking. The only potential overlap is create_checkout_link's live-pricing fallback, but its stated purpose and required quote_id flow make the boundary clear.

Naming Consistency5/5

All four tool names follow the same imperative verb_noun pattern in snake_case: create_checkout_link, get_parcel_quote, get_price_index, track_parcel. No mixed conventions or vague verbs.

Tool Count5/5

Four tools is a well-scoped set for a parcel shipping domain: one for quotes, one for checkout links, one for reference pricing, and one for tracking. Each tool earns its place without bloat or redundancy.

Completeness4/5

The core workflow is covered: get a quote, create a checkout link, and track the resulting label, with a free price-index tool for reference. Minor gaps exist around post-purchase lifecycle operations like voiding labels or retrieving session status, but those are not central to the stated purpose.