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

Goes well beyond the readOnly/idempotent annotations: no key required, no charge, no download (mediaUrl is HEAD-only), auto-inserted transcribe/translate steps, and unsupported dub languages surfacing in limitViolations rather than erroring. The only ambiguity is what happens when the plan itself is unusable — it implies violation reporting but doesn't say if the call still succeeds.

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?

The free/no-key/no-charge constraint is correctly front-loaded, and little is pure filler, but the steps sentence is a single 60-word clause pile that is hard to scan. A short bulleted op-to-parameter mapping would carry the same content with far less parsing cost.

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?

There is no output schema, yet the description enumerates the return shape well (steps with credits, totalCredits, totalUsd, freeAlternatives, feasible, limitViolations with code/limit/actual/unit/message/hint) and the balance behavior when a key is present. Completeness is only dented by the unmentioned voice parameter and style_preview op.

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 0%, so the description carries the burden and mostly does: it maps sub-parameters to ops (count/minSeconds/maxSeconds/reframe for shorts, keepSeconds for trim, renderer for burn, targetLanguage/voiceTier/sourceLanguage for dub) and explains source.durationSeconds/bytes/via/transcriptCues/mediaUrl plus hasTranscript/hasTranslation. Gaps remain: the 'voice' string parameter and the 'style_preview' op appear in the schema but are never mentioned.

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: 'Price a whole pipeline before running it and check it against the limits.' Immediately distinguishes itself from the execution siblings (caption_video, burn_captions, dub) by being the dry-run cost/feasibility check, and the opening 'Free, works without a key, never charges' reinforces that it is non-executing.

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?

Explicit about the timing: price before running, and the note that 'Paid tools return limit_exceeded with the same violations before charging' tells the agent what this buys them. It does not name the nearest alternative (quote or batch), so the agent must infer which of the two pricing paths applies.

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