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

Annotations already declare the mutation/safety profile (readOnlyHint false, destructiveHint false, idempotentHint false). The description adds valuable non-schema behavior: the render is non-destructive ('nothing is cut or re-rendered'), timing is approximate rather than word-level, runs asynchronously in the background, and crucially the billing outcome ('No speech is refused and refunded').

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?

Front-loads the core action and the .srt payoff in the first sentence, then layers defaults, timing caveat, source eligibility and billing. Dense but every sentence carries information; a few clauses could be trimmed without loss.

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 no output schema, the description sensibly covers the return form (the burned video plus the .srt, or srt-only with burn:false) and the async delivery path ('runs in the background and lands in the Library'). It does not explain how to poll or retrieve the finished job, a minor gap for a background tool.

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, but the description goes beyond it by explaining the burn flag's effect ('burn:false returns only the .srt'), the textStyle trigger condition, and the actual default look when textStyle is omitted — none of which the schema states.

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 (burn subtitles) and resource (existing video), plus a bonus artifact (the .srt). It is clearly distinguishable from neighbors like dub_video, edit_video, or recast_motion.

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 explicit when-to-use guidance for the optional textStyle ('only when the user describes a look') and clear source eligibility ('takes a /generated/ URL, a direct .mp4/.mov/.webm, or a YouTube/Vimeo/Loom-style link') with explicit exclusions ('not TikTok, Instagram or Facebook'). It does not name an alternative sibling tool, so it stops short of a 5.

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