Cycle audio output

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

No annotations are provided, so the description carries the full responsibility for behavioral disclosure. It does disclose key behaviors: it preserves mute state, reports measured default before and after, and supports dry-run. However, it does not clarify the nature of a dry-run (e.g., whether it performs an actual switch or only simulates), nor does it mention side effects, reversibility, or error conditions. This is adequate but not comprehensive for a mutation-style tool with no annotation safety hints.

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 concise (one sentence) and well-structured. It leads with the primary action, then adds the significant behavior (preserving mute state), then the reporting aspect, and finally the dry-run mention. It avoids unnecessary words and front-loads the core functionality. While it could be slightly more structured with bullet points, it is efficient and readable.

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?

Although this is a simple tool with one boolean parameter and no nested objects, it lacks an output schema and annotations. The description states it reports 'measured default before and after' but does not describe the format or structure of that report. It also does not define what constitutes an 'available output' or how failures are handled. Given the absence of annotation context and output schema, the description provides the main action but misses important details about return values and edge cases, making it only moderately complete.

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 has one parameter (dryRun) with a default but no description, and the description coverage is 0%. The description only states 'Supports dry-run', which does not explain the parameter's semantics—what dry-run does (e.g., simulate without changing state) or its effect on the output. The name 'dryRun' is self-explanatory to some extent, but given the lack of schema documentation, the description should clarify the behavior. It falls short of what an agent needs to understand the parameter's impact.

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 verb ('Cycle'), resource ('audio output'), and scope ('next available'), plus a distinctive behavioral guarantee ('preserving mute state'). It also specifies the output behavior ('report the measured default before and after'). This distinguishes it from related tools like audio_device_set_default (which sets a specific device) and audio_devices (which lists devices). The purpose is unambiguous and differentiated.

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. It implies usage for cycling through outputs but does not mention conditions such as 'when you want the next output' or 'instead of audio_device_set_default'. With a large sibling list including audio_device_set_default and media_source_switch, explicit routing guidance would be valuable. The description lacks any 'when to use' or 'when not to use' cues.

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