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

Annotations only declare the mutation profile (readOnly=false, destructive=false, idempotent=false), leaving the description to carry the rest — and it does: async job semantics, Pro-tier auth requirement, hard limits (60 segments, 30,000 combined characters), accepted voice-id provenance, and the job-id return contract.

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 sentences, each carrying distinct information: what it makes, the auth prerequisite, the hard limits, and the polling handoff. Front-loaded with the core action and free of filler.

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?

Even though an output schema exists, the description still supplies the auth requirement, quantitative limits, and the async job-id/polling contract an agent needs to drive the tool correctly. Nothing material is missing for a 4-parameter, non-nested schema.

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 75% and the description reinforces voice_a/voice_b meaning while adding a constraint absent from the schema: the 30,000-character combined text limit. The format parameter (mp3/wav, default mp3) is left unmentioned, which is the only minor gap.

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+resource ('Create a two-host (A/B) podcast episode') plus the execution model ('as an async job'). The two-host A/B framing distinguishes it from single-voice siblings like text_to_speech and generate_long_form without needing to open their schemas.

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?

Gives a clear precondition (Pro subscription key) and an explicit follow-up action ('poll get_job_status'), which is exactly what an agent needs after calling. It does not, however, state when to prefer a sibling such as text_to_speech or generate_long_form instead.

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