Live Stream

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

With no annotations, the description carries the full burden and does substantial work: localhost-only binding, the relay requirement for off-device pages, per-stream safety limiter, and the critical consequence that a stream plays sound wherever it is received ('tell the user first'). What remains undisclosed is lifecycle/idempotency — whether calling this starts or merely describes a stream, and how it relates to live_stop/stream_stop — which keeps it from a 5.

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 most important facts (targets, format, endpoint) are front-loaded, and every sentence contributes something — format, spatial use case, limiter, localhost/relay constraint, safety warning. It is a single run-on paragraph with an awkward mid-sentence line break around 'raw PCM (int16 little-endian...)', which costs some readability.

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?

An output schema exists, so return values need not be explained, and the description covers the safety and network-topology context an agent needs before calling a sound-emitting tool. The gaps are the unmentioned 'project' parameter and the unclear relationship to stream lifecycle siblings, but for a 2-parameter tool with an output schema this is close to sufficient.

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 coverage is 0%, so the description must compensate. It does so for 'name' by enumerating the accepted forms (master, 'bus:lucy', 'deck:A') and implying the default master. The required 'project' parameter is never mentioned anywhere, leaving one of two parameters undocumented in both schema and description.

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 specifies the resource and its scope precisely: a stream of the master, a bus ('bus:lucy') or a deck ('deck:A') as raw PCM int16 LE stereo 44.1 kHz over localhost. That is a concrete verb-less but unambiguous statement of what the tool provides. It does not name any sibling (live_bus, live_deck, stage_stream, stream_start, stream_status) to disambiguate, so it falls short of a 5.

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?

'A bus streamed on its own lets a VR stage play each object's sound at its place (route Lucy's tracks to bus lucy)' gives a real usage scenario for one mode. But it never says when to prefer this over live_bus, live_deck, stream_start, stream_status, or stage_stream, nor what conditions make a stream inappropriate. Guidance is implied by example rather than stated as when/when-not rules.

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