List Files

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

The description discloses a non-obvious behavioral detail: transparent retry with alternate Unicode normalization (NFC vs NFD) when path contains accented characters, including the confirmed device context (Mac/APFS-sourced devices). This goes well beyond the annotations (readOnlyHint=true, destructiveHint=false) and materially helps the agent understand and trust a fallback mechanism that would otherwise be invisible.

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 core purpose and followed by a dense but essential behavioral note. No filler or repetition of schema fields; every word contributes to understanding or safe invocation.

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 non-recursive list operation with clear annotations, the description covers the prerequisite (deviceId), the edge case (Unicode normalization), and the mental model (iDrive restore console). No output schema is provided, but the return value is reasonably inferable for such a listing tool, and the description does not leave an obvious gap for correct invocation.

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?

Although the input schema already documents all three parameters (100% coverage), the description adds meaningful context: path's accented-character handling during retries and deviceId's origin from list_devices. It reinforces what 'deviceId' means and adds a behavioral nuance for 'path' that the schema alone does not convey.

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 a specific action — 'Lists the files and folders backed up for a given device at a given path' — and identifies the resource as the device's backed-up file tree. It also differentiates from list_devices by naming that sibling as the source of deviceId, but it does not explicitly distinguish itself from the sibling browse_folder, which may overlap in purpose.

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 clear context: use this to browse a backed-up file tree at a given path, and explicitly instructs to use the sibling list_devices tool to obtain a deviceId. However, it does not mention when not to use this tool or cite alternatives such as browse_folder, so it stops short of a full usage-routing explanation.

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