handoff

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

With no annotations, the description carries the full behavioral burden. It does add valuable context beyond the schema: the transfer is lossless, preserves track and play position, and optionally sets target volume. However, it does not disclose side effects on the source device (does playback stop there?), failure behavior, or requirements like active playback or device availability — significant for a state-mutating tool with zero annotation coverage.

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?

A single sentence with the core behavior front-loaded, then the optional volume detail, then a concrete everyday example ('move to the kitchen speaker') that makes the intent instantly understandable. No filler, no repetition of schema content, and every clause 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?

Given no output schema, no annotations, and a rich sibling set, the description adequately covers the core action but leaves two gaps: explicit differentiation from the several near-identical device-transfer siblings, and the outcome/side-effect expectations (what the agent should report back, what happens on the source device). The well-documented parameters and the accurate core behavior keep it from falling below 3.

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 description coverage is 100%, so the schema already documents all four parameters thoroughly, including defaults, ranges, and formats. The description adds marginal value by clarifying that device_id is the target and volume applies to the target device after transfer, but it doesn't address dry_run or response_format, which remain entirely schema-dependent. 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 uses a specific verb ('Move playback') with a clear resource (another device) and the defining behavior: preserving the current track and play position, with optional target volume. The 'lossless' framing and the concrete 'move to the kitchen speaker' example effectively communicate the core function. It doesn't explicitly name sibling tools like transfer_playback or switch_device, but the emphasis on preserving state distinguishes it well enough.

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 'lossless' qualifier implicitly signals when to use this tool — when the user wants to relocate playback without losing the track or position, as opposed to a plain transfer or restart. However, the description provides no explicit when/when-not guidance or named alternatives, which is a real gap given the many adjacent siblings in the list (switch_device, transfer_playback, transfer_playback_with_state, pause_everywhere).

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