get_live_transcript

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

With no annotations, the description carries the behavioral burden well: it discloses polling/latency behavior, cursor advancement, wait behavior, rough text quality, and the stop condition. It does not describe failure behavior when no live recording exists, 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 description is front-loaded with the core purpose and behavior, then gives concise loop and reporting instructions. Despite being longer than a bare definition, every sentence supports correct invocation or use of the returned transcript.

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 that an output schema exists, the description does not need to explain return values, and it covers the live/polling workflow, cursor reuse, accuracy caveat, and stop condition. It is nearly complete, though it could say what happens if no live recording is active.

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, and it does: `since` is explained as the cursor for speech already heard and as the value returned from prior calls, while `wait_seconds` is explained as the maximum wait for new speech. Both parameters gain clear operational meaning beyond the bare schema.

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 names the specific tool action and resource: a live transcript of the recording in progress, limited to speech since the cursor. It also distinguishes itself from the final transcript by saying the post-call transcript is more accurate, so an agent can tell it apart from get_transcript.

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?

It gives explicit usage instructions: call in a loop within the same turn, pass the returned cursor as `since`, report useful findings to the user after each batch, and stop when the recording is over. It also states the prerequisite that the recording was started with live=true.

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