Skip to main content
Glama

get_order_history

Read-only

Retrieve past DoorDash orders to analyze ordering habits, find reorder targets, or locate a specific order; scan all results and re-query wider if the page is full.

Instructions

Past orders (default 50 orders / 90 days, max 100 / 365): store, items (item_id, name, quantity), order_date, order_fulfilled_at, order_uuid, is_reorderable, fulfillment_type, is_group_order. Rows carry no total and no per-item price — use get_receipt for money. Use to analyze habits ('my usual'), find reorder targets, or locate a specific past order (scan all results; if page_full, re-query higher/wider).

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": {
      "intent": "<intent>"
    },
    "name": "get_order_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxNoMax orders 1-100 (default 50)
daysNoWindow in days, up to 365 (default 90)
intentYesOne short line stating who this is for and the goal, e.g. 'Help the user order dinner'. DO NOT include the user's verbatim words, dietary/health/religious details, budgets, names, or other personal specifics — a generic goal is expected.
include_group_orderNoAlso return group orders the user hosted or joined — pass when the question is about a team/office/shared order

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.0
    • addedInput schema / properties / include_group_order
      Added value: +{
      +  "description": "Also return group orders the user hosted or joined — pass when the question is about a team/office/shared order",
      +  "type": "boolean"
      +}
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnlyHint/destructiveHint/openWorldHint), so the description is free to add behavioral detail — and it does: window and row caps, the fact that results omit totals and per-item prices, and the pagination-completeness signal (page_full). It never names the actual response envelope or what page_full belongs to, so the agent must infer return shape.

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?

Front-loads scope and caps, then the returned fields, then the critical omission caveat, then usage — a sensible order. The field enumeration is dense and terse to the point of being hard to parse, but no sentence is wasted.

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 no output schema, the description must carry the return shape, and it largely does by listing the returned fields and explicitly flagging the missing money data. The one loose end is page_full, referenced as a signal without stating which response field carries it or what the rest of the envelope looks like.

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 max, days, intent, and include_group_order are already fully documented, establishing the baseline of 3. The description's 'default 50 / 90 days, max 100 / 365' restates the schema rather than adding new semantics, and it says nothing extra about how intent is used.

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+resource (past orders) and immediately scopes it with default/max limits and the exact fields returned (store, items, order_date, order_uuid, etc.). It also distinguishes itself from get_receipt by declaring that rows carry no money data, so an agent can separate it from a receipt-fetching sibling without opening 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?

Explicitly names three concrete use cases (analyze habits, find reorder targets, locate a specific order) and names the alternative for a different need (get_receipt for money). It also gives procedural guidance for the ambiguous case: scan all results and, if page_full, re-query with higher/wider limits.

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