start_playback

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

With no annotations the description carries the full burden, and it delivers real behavioral context: the mutation happens 'in one undo-scoped command' (undo semantics an agent otherwise couldn't know) and the call can be rejected during shutdown. It omits whether the operation is reversible via a single undo step client-side and what state is affected beyond playing.

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?

Four short, front-loaded labelled lines (purpose, side effects, example, edge cases) with no filler; an agent can scan it in one pass. The example line is slightly redundant in phrasing but does supply return-behavior information not available elsewhere.

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 trivial no-arg tool with no annotations and no output schema, the description covers purpose, mutation scope, undo scoping, the observed return state, and a failure mode, which is close to sufficient. Minor gaps remain around whether record-arm or song position interact with the start.

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 tool takes zero parameters, so per the baseline there is nothing for the description to disambiguate. It correctly says nothing about argument syntax, which is appropriate for a no-arg call.

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?

States a specific verb and resource: 'Start Live's transport,' which an agent can immediately map to a playback-start operation. It does not, however, name or distinguish itself from the clearly related sibling stop_playback (nor from fire_clip/fire_scene), so sibling differentiation is left to inference.

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 purpose is unambiguous enough that usage is implied, and the edge-case note ('Live can reject the call while shutting down') warns of one failure context. But it never states when to prefer this over stop_playback or the clip/scene firing tools, so no explicit routing guidance is provided.

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