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

Adds significant behavioral context beyond what annotations provide: the operation 'Spends AI credits' (a cost consequence), is queued asynchronously rather than executing synchronously, and 'returns a job to poll' — all unstated in the annotations. The annotations cover idempotency and non-read-only status, and the description is fully consistent with them, while enriching the agent's understanding of side effects and workflow.

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?

Two sentences with zero waste. The action and resource are front-loaded in the first sentence, and the second sentence delivers the two highest-stakes facts — cost and async polling — that an agent must know before invoking. Every word earns its place.

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?

With an output schema present to document the job return shape, 100% schema coverage, and annotations covering idempotency/safety, the description covers the remaining essentials for an async queue tool: what is produced, where it lands, that it costs credits, and how to follow up (poll with generation_jobs_get). Nothing an agent needs to call it correctly is missing.

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 100%, so the schema already documents all 6 parameters well, including the voiceId catalog lookup (generation_options_list with kind voiceover), speed range, voiceStyle enum, and idempotencyKey semantics. The description adds minimal parameter-level meaning beyond confirming 'text' is the read-aloud script via the 'text-to-speech' phrasing. Baseline 3 is appropriate since the schema carries the heavy lifting.

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?

Uses a specific verb ('Queue') and names a precise resource ('text-to-speech voiceover into the BlitzReels media library'). The async nature ('returns a job to poll') clearly distinguishes this from synchronous siblings, and the 'text-to-speech voiceover' scoping separates it from the generation_music_create, generation_sound_create, generation_video_create, and generation_faceless_create siblings without needing to open any schema.

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 establishes clear context for when to use this tool: when a voiceover is needed and the caller expects an async queued job. The explicit pointer to generation_jobs_get gives the follow-up workflow, and the TTS scoping implicitly routes the agent away from the music/sound/video/image generator siblings. It stops short of explicitly enumerating when-not-to-use conditions, so it doesn't reach a 5.

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