remarkable_delete

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

Annotations already mark destructiveHint=true, and the description reinforces this while adding substantial detail: items are moved to Trash by default, permanent=True removes the resolved UUID and sidecar files, confirmation is required unless skipped, and defer_restart triggers a refresh_pending flag. This significantly enriches the behavioral model beyond the annotation.

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 well-structured with usecase, instructions, parameters, and examples. Each section is dense with useful information without redundancy. The front-loaded usecase immediately states the purpose, and the instructions convey critical safety and mode details efficiently.

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?

The description covers all key aspects: default Trash behavior vs permanent deletion, mode availability (cloud/SSH, not USB), confirmation mechanics, parameter nuances, and example invocations. Even though an output schema exists, the description sufficiently contextualizes the operation for a destructive tool with mode-specific behavior.

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?

While the schema only lists titles and types, the description's <parameters> section explains each parameter in practical terms: 'document' is a name/path, 'permanent' is SSH-only and removes files permanently, and 'defer_restart' is SSH-only and skips restart to batch deletes. This fully compensates for the 0% schema description coverage.

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 opens with a clear statement: 'Delete a document or folder on the reMarkable tablet.' This specifies the verb (delete), the resource (document or folder), and the scope (reMarkable tablet), effectively distinguishing it from sibling tools like remarkable_move or remarkable_rename.

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 provides explicit usage context: it works in cloud and SSH modes (not USB web interface), is destructive by default, and explains when permanent deletion should be used ('only when the user explicitly asked for permanent deletion'). It also covers confirmation behavior and the defer_restart option, giving clear guidance on when and how to invoke the tool safely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.