remove_order_itemRemove a line item from an order. Recomputes the order total. Use get_order to find the order's externalId and the item's itemId. The result echoes the operating workspace.
| Name | Required | Description | Default |
|---|---|---|---|
| itemId | Yes | The order item id returned by get_order. | |
| externalId | Yes | The order externalId returned by list_orders or create_order. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, but the description adds valuable behavioral context by stating 'Recomputes the order total' and 'The result echoes the operating workspace', both of which go beyond the structured metadata to clarify side effects and result behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three concise sentences: it states the action, the side effect, and a necessary prerequisite. Every sentence serves a purpose with no fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter destructive operation, the description covers the action, side effect, and how to obtain parameters. It does not explain error cases or what happens if the item is not found, and the phrase 'result echoes the operating workspace' is somewhat vague, preventing a perfect score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% parameter documentation, describing both externalId and itemId with their sources. The description simply repeats the instruction to use get_order, adding no new semantic meaning beyond what the schema already states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Remove a line item from an order' with a clear resource and scope, and inherently distinguishes itself from sibling tools like add_order_item and update_order_item through the action 'Remove'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear usage context and explicitly instructs to use get_order to find the required externalId and itemId. However, it does not mention when not to use this tool or contrast with alternatives like update_order_item or add_order_item, so it stops short of full guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are generally separated by entity and action, with helpful cross-references such as get_marketplace vs list_channel_products vs check_channel_readiness. The main soft spots are update_product vs adjust_stock for stock changes and the many list_/search_/get_ triplets, but descriptions mostly make the boundaries clear.
All tools follow a consistent lowercase snake_case verb_noun pattern: create_*, get_*, list_*, search_*, update_*, transition_deal, configure_pipeline, and so on. Despite the large count, the naming is highly predictable.
52 tools is an extreme surface for an agent to reason over, even though the underlying domain is broad. The set could be consolidated substantially without losing core functionality.
Most core lifecycle workflows are covered across leads, contacts, companies, products, orders, and activities. However, there are notable gaps: deals cannot be updated except by stage transition, activities cannot be edited or rescheduled, and there are no delete operations at all, only status-based archiving.