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

Goes meaningfully beyond the annotations by disclosing that the call is billable, that it only starts the work rather than completing it, and that the returned receipt is durable — cost and async semantics are not encoded anywhere in the structured fields. What's missing is the operational consequence: whether the result must be polled and via which tool. Note the tension between the constructive framing and destructiveHint=true, though the description does not assert anything the annotation directly forbids.

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?

A single tight sentence with the key facts front-loaded: cost, action, precondition, and return type. No filler, no repetition of the title.

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?

The output schema covers the receipt, so return values needn't be spelled out, and the input schema covers validation. But for an async 'start' tool with a billable side effect, the description omits the most decision-relevant fact — how to obtain the finished summary and whether the call is retryable against an existing key.

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 carries the full burden for both parameters and does not mention either. 'Durable operation receipt' hints loosely at why an idempotencyKey exists, but nothing explains the transcriptionId's expected format or what idempotency scope means in practice (per-transcript? per-key collision behavior?).

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 outcome ('Starts a billable AI summary') on a specific resource ('a completed transcript') plus a return shape ('durable operation receipt'). An agent can tell it produces a summary rather than raw text, but it never distinguishes itself from nearby summarization-adjacent siblings like generate_chapters, translate_transcript, or repurpose_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?

The phrase 'for a completed transcript' supplies a real precondition (the transcript must already be transcribed), which is more than most tools offer. However, it gives no explicit when-not guidance and never names the follow-up or alternative tools (get_job_status, list_operations, get_transcript_artifact), leaving the agent to infer the rest of the flow.

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