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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered elsewhere. The description still adds genuinely useful non-annotation context: it costs 1 credit and takes roughly 1–2 minutes for video input, and it notes the AI actually watches the supplied video. Slight blemish: 'Instant (up to ~1–2 min for videos)' is internally inconsistent about latency.

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?

One dense, front-loaded sentence with the verb and resource first; the parentheticals about video watching and timing earn their space. Minor waste and awkwardness in 'Costs 1 credit(s)' and the self-contradicting 'Instant (...1–2 min)'.

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 8 params, 17 enum languages, annotations present and no output schema, the description covers inputs, cost, latency and the nature of the result well. The notable gap is that nothing says what comes back — a script string, an object with fields, an id to poll — which is the one thing an agent still has to guess without an output 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 100%, so the baseline is 3 and the schema already carries enum and format detail. The description still adds meaning the schema does not: target_seconds sizes the output rather than merely bounding it, and 'the AI watches it' explains why url/upload_id matter. It stops short of explaining genre's effect on output beyond naming it.

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 resource ('Write a viral voiceover/narration script') and immediately disambiguates the two accepted inputs: a video via url/upload_id, or a text to rewrite/expand. An agent can tell this produces a script, not audio or a finished video, which separates it from generate_voiceover or create_short without opening a 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?

It implies when the tool applies ('for a video ... or rewrite/expand a text') and makes the url/upload_id vs text inputs mutually exclusive, which is real usage guidance. However it never names a sibling alternative or states when NOT to reach for this over generate_voiceover, create_short or studio_generate, leaving routing to inference.

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