Soft-delete a document by id and cascade soft-delete its attachments; none of them appear in listings afterward, but the records are retained rather than permanently erased.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The id of the document to delete, as returned by create_document or list_documents. |
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | ||
| title | No | ||
| message | No | ||
| variant | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (destructiveHint), the description discloses that deletion is soft, records are retained, attachments are also soft-deleted, and none appear in listings. This is substantial behavioral context not inferable from annotations alone.
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 one sentence, front-loaded with the verb and object, and communicates the core behavior, cascade, retention, and listing impact without any filler 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?
Given the tool's simplicity (one parameter, output schema exists, annotations provided), the description covers all essential aspects: what happens to the document, attachments, listing visibility, and data retention. No significant gaps remain.
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 already fully describes the id parameter, including its origin ('as returned by create_document or list_documents'). The description's 'by id' adds no new parameter-level semantics, but with 100% schema coverage, the baseline of 3 applies.
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 states 'Soft-delete a document by id and cascade soft-delete its attachments,' which explicitly names the action, resource, and scope. It distinguishes from other delete_* tools by specifying soft-delete behavior and the cascade to attachments.
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 does not explicitly state when to use this tool versus alternatives, but the resource-specific scope is clear. It lacks guidance on exclusions or alternative tools (e.g., hard delete or undo), so usage context is only implied.
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.
Each tool targets a distinct resource and action, with clear descriptions separating similar-sounding tools like create_calendar_event vs create_recurring_calendar_event. Shopping list operations (add, buy, remove, update) are clearly delineated.
All tools follow a verb_noun snake_case pattern: create_*, list_*, update_*, delete_*, get_*, etc. Even special operations like store_memory, recall_memory, and skip_recommendation fit the pattern.
With 68 tools, this server vastly exceeds a reasonable scope; the instruction manual indicates 50+ tools is an extreme mismatch. The breadth suggests the server should be split into focused sub-servers (tasks, shopping, calendar, etc.) rather than a single monolithic interface.
The tool surface covers full CRUD/lifecycle for all major resources: tasks, shopping, calendar, contacts, documents, appliances, vehicles, pets, recipes, meal plans, subscriptions, and memories. Additional features like house review, weather, and profile round out the household management domain.
