Skip to main content
Glama

SMKlog Parcel Shipping Rates

by com.smklog

Check a checkout session

get_checkout_status
Read-onlyIdempotent

Reports where a payment session made by create_checkout_link stands: whether the human has opened checkout, paid, and whether the shipping label exists yet, with the tracking number once it does. Reads SMKlog's own order records only: no carrier call, no quote allowance, nothing changes. Poll it after handing the human the link, minutes apart rather than seconds, because nothing moves until the human acts.

Statuses, in order: awaiting_checkout (link made, no checkout started), checkout_started (a checkout exists, not paid), paid (paid, label not created yet: the checkout page buys it right after payment, otherwise an operator picks it up), label_ready (label bought, tracking_number present), delivered, refunded. Once label_ready, feed tracking_number to track_parcel for scan events.

Parameter rules:

  • session_id is the session_id returned by create_checkout_link, shaped as_ plus a UUID. Nothing else identifies a session: no order id, no email, no quote_id.

  • A session lives 30 days from creation. An unknown, malformed or expired id answers session_not_found rather than a status.

  • The answer never carries names, addresses or emails. Treat the session_id like a tracking number: whoever holds it can read the tracking number.

  • A manual-review request made from the handoff page is not a checkout and leaves the status at awaiting_checkout.

  • Allowance: 60 checks an hour per client.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
session_idYesThe session_id from create_checkout_link.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
nextNoWhat, if anything, the agent should do now
amountNoThe amount the session was anchored to, USD
statusYesStage, in that order
serviceNoThe service the session was anchored to
checkoutNoThe checkout the human started, null while awaiting_checkout
currencyNoISO currency, USD
created_atNoWhen create_checkout_link made the session, ISO 8601
expires_atNoWhen the session stops answering, ISO 8601
session_idYesThe session asked about
quote_reusedNoWhether the session reused a quote_id

TDQS

A5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds substantial context beyond them: the 60/hour rate limit, 30-day session lifetime, session_not_found behavior for expired/malformed IDs, and the privacy constraint that responses never carry names, addresses, or emails. The 'nothing changes' statement aligns perfectly with readOnlyHint=true, so there is no contradiction.

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?

Roughly 200 words, but every paragraph earns its place: purpose and polling cadence, status semantics with transition details, ID rules, the manual-review edge case, and the rate limit. Content is front-loaded with the core statement and grouped under a clear 'Parameter rules' heading rather than dumped as a wall of text.

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?

With an output schema covering the return envelope, the description covers everything else an agent needs for correct invocation: polling cadence, status ordering and transition semantics, the error condition (session_not_found), TTL, rate limit, privacy constraints, and follow-up routing to track_parcel. Nothing operational is missing.

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?

Schema coverage is 100%, yet the description still adds real meaning: the ID's provenance ('the session_id returned by create_checkout_link'), its shape ('as_ plus a UUID'), and explicit exclusions ('no order id, no email, no quote_id'). It also conveys sensitivity posture ('treat the session_id like a tracking number'), which the schema cannot express.

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 opens with a specific verb and resource ('Reports where a payment session made by create_checkout_link stands') and enumerates the exact statuses returned, so an agent knows precisely what this tool does. It also differentiates from siblings by naming track_parcel as the follow-up tool and framing itself as a read-only status check, which no sibling claims.

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?

Explicit when-to-use guidance is present: 'Poll it after handing the human the link, minutes apart rather than seconds,' with the rationale that nothing moves until the human acts. It also routes to the alternative tool explicitly ('Once label_ready, feed tracking_number to track_parcel') and rules out other uses with 'no carrier call, no quote allowance.'

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

All SMKlog Parcel Shipping Rates toolsInspect
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

A4.9/5.0
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.

Resources