Remove one or more items from the user's Grabblist (soft-delete). Pass a single id or an array of ids for batch operations.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Item ID or array of item IDs to delete | |
| reason | No | Why this change was made (shown to user in change history) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as destructive and non-read-only. The description adds valuable context beyond those hints by specifying 'soft-delete' (indicating the operation is recoverable) and noting that the reason parameter is shown to the user in change history. No contradiction with annotations.
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?
Two sentences, front-loaded with the main purpose, no redundancy. Every word earns its place.
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 mutation tool with 2 parameters and solid annotations, the description is complete. It explains the core behavior (soft-delete), batch support, and the schema covers the reason field. No output schema exists, so return-value detail is not required.
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?
Schema coverage is 100%: both id and reason have descriptions. The description restates id flexibility ('single id or array') but adds no new semantic detail beyond what the schema already provides. Baseline 3 is appropriate.
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 clearly states the action: 'Remove one or more items from the user's Grabblist (soft-delete).' It specifies a concrete verb and resource, distinguishing it from sibling tools like delete_collection (targets collections) and restore_item (the inverse operation).
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?
Provides clear context that this is for removing items and mentions batch operations, which is useful guidance. However, it does not explicitly name alternatives or exclusion cases (e.g., 'use delete_collection for collections' or 'use restore_item to undo'), though the soft-delete hint implies reversibility.
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.
Most tools have clearly distinct purposes with no obvious duplicates. The only potential overlap is between update_item and update_price, but the descriptions clarify that update_price is specifically for manual price corrections with history tracking.
All tool names follow the snake_case verb_noun pattern consistently (e.g., add_item, create_collection, get_item_graph). Slight deviations like add_to_collection and ping are still predictable and conventional.
With 23 tools, the server sits in the heavy range (16-25). While each tool serves a distinct purpose, the count is higher than typical for a shopping-save app and may feel overwhelming, though not excessive.
The tool surface covers full CRUD for items and collections, relations, history, activity, and utilities. Minor gaps exist—such as no dedicated 'move item between collections' tool—but workarounds are possible using existing tools.
