Skip to main content
Glama

Order: Refresh Supplier Details

update_supplier_order

[Order] [What it does] Starts an asynchronous refresh of supplier order details for one store or all owned stores; does not return refreshed data immediately. [When to use] Use when supplier order details (such as tracking or status) look stale or missing and must be refreshed before rereading the order; commonly the final write-back step in flows like Order Address Fix. [When not to use] For reading existing data without a refresh, use get_order or list_orders; to change order content itself, use the order-update tool, not this one. [How to use] Copy dsers_store_id from list_stores; omitting it covers all owned stores, so confirm scope first. A successful response returns task_type and task_id; use both with get_job_status until terminal=true. The response means only that the asynchronous job was created, not that supplier details are already refreshed. Dispatch once; if the outcome is unknown, poll the returned task instead of resubmitting. [Side effects] Creates a synchronization job that may update stored supplier details. [Confirmation] Requires non-skippable user confirmation; show the exact store scope first. [Follow-up] After the task reaches a successful terminal state, verify updated supplier details with get_order or list_orders; if it fails, report the task status and message, then 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": "update_supplier_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
dsers_store_idNoCopy from list_stores response. Optional — omit to refresh all owned stores.

Output Schema

NameRequiredDescriptionDefault
task_idYesDSers sync job ID as a decimal string
task_typeYesFixed value supply_order_sync
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

A4.9/5.0
Behavior5/5

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

Goes well beyond the annotations (which only declare non-readOnly, openWorld, non-idempotent, non-destructive): it discloses the asynchronous job semantics, the exact response fields (task_type, task_id), the poll-until-terminal contract, the side effect of mutating stored supplier details, and a non-skippable user confirmation requirement. The 'dispatch once' instruction is consistent with idempotentHint=false rather than contradicting it.

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?

Strongly front-loaded and sectioned with bracketed labels so an agent can jump to the needed part. Minor redundancy: the no-immediate-return caveat appears both in the purpose line and again in the how-to-use block, which slightly inflates an otherwise tight definition.

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?

Complete for an async, confirm-gated mutation: prerequisites, confirmation behavior, expected response fields, polling loop, and post-success verification are all covered. Since an output schema exists, the description stops short of describing full return payloads, which is appropriate.

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?

With one fully documented parameter the schema baseline is 3, but the description adds operational meaning: where the value comes from (list_stores), that omission widens scope to all owned stores, and that the scope must be confirmed before dispatch. That is context the schema does not carry.

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 ("Starts an asynchronous refresh of supplier order details") plus the scope (one store or all owned stores) and immediately corrects the likely misconception that data is returned inline ("does not return refreshed data immediately"). It explicitly differentiates from get_order/list_orders and from the order-update tool.

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?

Has explicit when-to-use (stale/missing tracking or status, final write-back step in flows like Order Address Fix) and when-not-to-use sections that name the alternatives (get_order, list_orders, the order-update tool) and the condition selecting each. Guidance also covers re-dispatch behavior: poll the returned task instead of resubmitting.

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.