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

Annotations already say readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses that nothing is charged, that it works unauthenticated in one mode, that duration is probed from media in the other, per-operation pricing units, and the caveat that a trim media quote is an upper bound. These are exactly the behavioral facts an agent needs before calling a pricing tool.

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-loaded with the single most important fact ('Free'), then prerequisites, then a per-operation rate table. Dense but every clause carries pricing or invocation information; the semicolon-chained rate list is harder to scan than it could be but nothing is 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?

Seven parameters, no output schema, and the description does explain the unit of the return value (cents/credits) plus that dub quotes include a breakdown. It stops short of describing the general response shape or what an unknown/failed probe returns, which matters given the media-probing mode.

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?

With only 43% schema description coverage, the description carries most of the burden and mostly does: it explains the durationSeconds vs fileId/mediaUrl tradeoff, ties voiceTier to dub (basic vs standard), translateTo to caption, and targetLanguage to dub. Gap: the enum value 'style_preview' is present in the schema but never mentioned, and fileId vs mediaUrl is not distinguished from each other.

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?

Opens with a specific, unambiguous statement of what the tool does: returns cents/credits a job would cost without charging. That distinguishes it from the execution siblings (caption_video, dub, transcribe) which actually spend credits. It never names the potentially confusable sibling 'plan', so differentiation from that one is left to inference.

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 concrete invocation contexts: no key needed if you pass operation + durationSeconds, keyed usage allows fileId or mediaUrl with duration probed automatically. That is real when/how guidance. It does not state when to prefer this over plan or when a quote is unnecessary (e.g., already knowing the rate), so no explicit exclusions.

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