Skip to main content
Glama

Tracking: Browse Packages

list_packages
Read-onlyIdempotent

[Tracking / Logistics] [What it does] Lists account-owned packages by normalized logistics status; read-only. [When to use] Use when packages that are pending, in transit, delivered, in an exception state, or flagged for attention are needed. [When not to use] For the tracking events of one known package, use get_package_details instead of this tool. [How to use] Filter with status=all, status=pending, status=in_transit, status=delivered, status=abnormal (all exception packages), or status=attention (flagged packages). You can also filter by order/tracking keyword, store, supplier platform, order age, or Unix time range; page_size caps at 100; reuse the previous next_cursor to page. An empty items array is valid; has_more=true means more results remain. [Side effects] Read-only. [Confirmation] No confirmation required. [Follow-up] If a package is in an exception or appears overdue, inspect it with get_package_details; otherwise report the result and stop.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_packages"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNoOpaque next_cursor returned by a previous call.
statusNoTracking tab: all, pending, in_transit, delivered, abnormal (exceptions), attention (flagged).
keywordNoOrder or tracking number search text. Optional.
end_timeNoOptional Unix end timestamp.
page_sizeNoItems per page, up to 100.
search_byNoHow keyword should be interpreted.
sort_orderNoCreation-time sort order.desc
start_timeNoOptional Unix start timestamp.
dsers_store_idNoOptional DSers store ID as a decimal string.
detail_statusesNoOptional detailed logistics statuses. Paste JSON example: ["awaiting_shipment","in_global_transit"].
sales_order_age_daysNoOptional sales-order age in days.
supplier_platform_idNoOptional supplier platform application ID as a decimal string.

Output Schema

NameRequiredDescriptionDefault
itemsYesTracking packages
countsYesPackage counts by tracking tab
paginationYesStable cursor pagination
toolcall_response_atYesUTC timestamp when the Tool response was returned, formatted as RFC3339.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description's repeated "read-only" and "no confirmation required" add little. Where it earns credit is pagination and result-shape behavior that annotations cannot express: page_size capped at 100, reusing the previous `next_cursor`, an empty `items` array being valid, and `has_more=true` meaning more results remain.

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

Conciseness4/5

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

The bracketed section headers make it easy to scan and front-load the purpose, usage, and exclusions. It is on the long side and repeats "read-only" in both the purpose and side-effects lines, but for a 12-parameter tool with six status tabs the length is largely earned rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the definition needn't describe return values, yet it still covers the pagination contract, empty-result case, and follow-up behavior, which is what an agent actually needs. Minor remaining gap: `detail_statuses` and `search_by` interpretation are left entirely to the schema.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents every parameter, and the description's enumeration of status values largely restates the enum. It adds only light glosses such as "abnormal (all exception packages)" and "attention (flagged)," while leaving the interplay between `keyword` and `search_by` and the `detail_statuses` values unexplained. Baseline 3 is appropriate when the schema carries the semantics.

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?

States a specific verb and resource (lists account-owned packages) plus the organizing dimension (normalized logistics status) and scope boundary (account-owned, read-only). It also explicitly separates itself from `get_package_details` by targeting collections rather than one known package, so an agent can route between them without opening a schema.

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 definition has explicit "When to use" and "When not to use" sections, naming `get_package_details` as the alternative for per-package tracking events. It also closes the loop with a follow-up rule: escalate to `get_package_details` only for exception or overdue packages, otherwise report and stop.

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.