Skip to main content
Glama
smklog

SMKlog Parcel Shipping Rates

Create a payment session for a shipping label

create_checkout_link

Turn a parcel quote into a paid shipping-label checkout: pass a quote_id to reuse its price and get a handoff URL plus session_id. Track payment status with get_checkout_status.

Instructions

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
Install Server

TDQS

A5/5.0
Behavior5/5

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

The description goes well beyond annotations by disclosing side effects: it writes a 30-day session record, is not idempotent, spends carrier calls when no quote_id is used, never charges the card, and calls out stale-link repricing. It also explains failure conditions like missing_required_fields. This is exactly the behavioral context an agent needs.

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: main behavior, side effects, no-session cases, and parameter rules are clearly separated. It is front-loaded with the core purpose and workflow placement, and the later formatting uses scannable paragraphs and labeled parameter rules.

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 7-parameter tool with subtle override rules and special-case failures, the description is remarkably complete: it explains the quote_id interaction, fallback behavior, service matching, international customs/duty, and what the human completes on the resulting page. The output schema exists, so the description does not need to restate return structure, and it covers what the schema cannot.

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?

Even though schema coverage is 100%, the description adds substantial semantic value: quote_id overrides most fields but not service, expired quote_ids fall back to live pricing, service matching is a case-insensitive fragment that silently falls back to cheapest, and from_zip/to_zip constraints are clarified. These rules are absent from the schema and materially change how parameters should be supplied.

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 names a specific verb and resource: 'Turns a decided shipment into a payment session for buying its shipping label.' It clearly distinguishes itself from quote/session-status siblings by describing the handoff URL and session creation, and it orients the agent to the surrounding workflow with 'Use it after get_parcel_quote.'

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?

It explicitly says when to use the tool ('after get_parcel_quote') and when not to ('No session is returned when... freight, oversize...'), and names the sibling get_checkout_status for checking human payment and label existence. These are concrete, actionable routing rules rather than vague context.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/smklog/parcel-shipping-rates-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server