audition_context_tool

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

With no annotations, the description carries the burden and does disclose meaningful behavior: it does not play audio, visual mode is slower, times are in timeline/session seconds, and the return payload is audition_context.v2. It does not explicitly state read-only/non-mutating or explain the clip-skew/render-freshness concept, but for an inspection tool this is reasonably transparent.

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 compact and uses a clear detail-level breakdown, with the key no-audio caveat placed at the end. The opening phrase 'Caption each dialogue track...' is awkward and partially wastes the first sentence, but overall every sentence adds functional information.

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-value details do not need to be in the description. The tool still leaves some gaps: the meaning of 'clip-skew / render freshness', the role of skew_warn_sec, and how suggested_listen should be used are not explained; an agent might invoke it correctly by name and required params but without full confidence in interpretation.

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 0%, so the description must compensate. It clearly documents detail and its three variants, and implies start_sec/end_sec define the timeline window with seconds units. However, skew_warn_sec and project_path are not directly explained; skew_warn_sec's role is only vaguely hinted at by 'clip-skew / render freshness'.

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 identifies the resource (dialogue tracks in a timeline window) and says the tool returns audition_context.v2 with typed hypotheses, suggested_listen, and clocks, so an agent can roughly tell what it does. However, the leading verb 'Caption' is vague/possibly a typo, and it is not differentiated from many other inspection/context siblings (e.g., build_edit_context, get_session_state_tool).

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 gives useful selection guidance for the detail parameter (summary/full/visual, with visual slower) and explicitly notes the tool does not play audio, which rules out playback use. It does not name any alternative tool or say when to prefer this over other context/status tools, so usage guidance is only implied.

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