Remove one or more items from a collection. Pass a single item_id or an array of item_ids for batch removal. Items are NOT deleted — they stay in the Grabblist.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | Why this change was made (shown to user in change history) | |
| item_ids | Yes | Item ID or array of item IDs to remove | |
| collection_id | Yes | The collection ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide readOnlyHint=false, destructiveHint=false, and idempotentHint=true, but the description adds crucial behavior beyond these: it clarifies that items are NOT deleted, which is a key nuance that could otherwise be misunderstood. It also discloses batch removal behavior, adding value beyond the structured 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?
The description is two concise sentences, front-loaded with the main action, and includes a critical caveat. Every sentence adds value, with no redundant information.
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?
Given the tool's moderate complexity, full schema coverage, and presence of annotations, the description is complete. It explains the core operation, the batch capability, and the non-destructive nature. No output schema exists, so not explaining return values is acceptable.
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 schema covers all parameters with descriptions (100% coverage), so the baseline is 3. The description merely restates the batch/array option already present in the schema ('Pass a single item_id or an array of item_ids') but adds no new meaning for the 'reason' or 'collection_id' parameters.
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 a collection.' It distinguishes from sibling tools like delete_item by explicitly noting that 'Items are NOT deleted — they stay in the Grabblist.' This provides a specific verb+resource+scope and differentiates it from similar operations.
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: it explains batch removal via a single item_id or array, and the non-deletion warning tells users this is not the tool for permanent deletion. However, it does not explicitly name alternatives like delete_item or restore_item, so it misses the 'explicit when-not' threshold for a 5.
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.
