Skip to main content
Glama

Tracking: Get Events

get_package_details
Read-onlyIdempotent

[Tracking / Logistics] [What it does] Reads the logistics status, attention flag, and carrier event snapshot that DSers holds for one tracking number on the authenticated account. [When to use] Use it when the user asks where a shipment is or why it has stalled, and whenever the agent needs event evidence before handling a delivery exception or replying to a buyer. Trigger words: where is my package, check this tracking number, delivery exception, when will it arrive. [When not to use] It looks up tracking numbers only and cannot return every package on an order; get the tracking number from get_order first. To write a tracking number back to a store order, use sync_existing_tracking_numbers_to_store. External numbers outside this account cannot be queried. [How to use]

  • tracking_number is required and must belong to this account; a number supplied by a buyer cannot be looked up directly.

  • Events are not necessarily newest first; compare timestamps to identify the latest checkpoint.

  • Event times use the carrier's own format; a normalized timestamp and timezone appear only when available, so confirm the timezone before comparing times.

  • An empty event list is a valid result meaning no scans yet; it does not prove the parcel is unshipped or lost. Estimated delivery is not returned and must not be inferred.

  • The data is a stored DSers snapshot that can lag the carrier site. The attention flag is only a marker, not a confirmed exception. [Side effects] None; read-only. [Confirmation] Not required.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tracking_number": "<tracking_number>"
    },
    "name": "get_package_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
tracking_numberYesCopy tracking number from list_packages results. Required.

Output Schema

NameRequiredDescriptionDefault
eventsYesTracking events; use event timestamps to determine chronological order
attentionYesWhether marked for attention
tracking_statusYesCurrent logistics status
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

A4.8/5.0
Behavior5/5

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

Annotations already cover the read-only/idempotent profile, but the description adds substantive behavior: the data is a stored DSers snapshot that can lag the carrier, events are not guaranteed newest-first, empty event lists are valid and do not prove non-shipment, and the attention flag is a marker rather than a confirmed exception. It also states what is NOT returned (estimated delivery), which prevents an agent from inferring unsupported values.

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?

Heavy bracketed sectioning is front-loaded and scannable, with the core purpose and the routing exclusions in the first three blocks. A few lines (timezone formatting, timestamp comparison) are borderline operational detail, but each still supports correct interpretation rather than restating structured fields.

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?

The tool is a single-parameter read with an output schema, and the description covers everything the agent needs beyond that: sourcing the input, account scope, staleness of the snapshot, event ordering, and what cannot be inferred. Nothing required to invoke or interpret the call 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?

Schema coverage is 100% and the single parameter is documented in the schema, so the baseline is 3. The description earns above baseline by adding a constraint absent from the schema: the tracking number must belong to the authenticated account and cannot be one supplied by a buyer. A minor note is that the description points to get_order for sourcing the number while the schema points to list_packages, which is a small inconsistency rather than a contradiction.

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: reads logistics status, attention flag, and carrier event snapshot for one tracking number on the authenticated account. It explicitly distinguishes itself from list_packages (all packages) and get_order (resolving tracking numbers), so an agent can select it without inspecting the 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?

Provides explicit when-to-use triggers ("where is my package", delivery exception, buyer reply), a when-not-to-use section naming two alternatives (get_order, sync_existing_tracking_numbers_to_store), and a hard boundary that external or buyer-supplied numbers cannot be queried.

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.