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

Goes well beyond the annotations (readOnlyHint, idempotentHint false) by disclosing hard limits (~18,000 chars/call, ~20 min of speech, daily per-user and total allowances), cost (~$0.0002 per 1,000 chars), the models used (m2m100, small Llama for trimming), the fitting behavior of dub lines (ok/tight/long), and that nothing is stored. These are behavioral traits an agent needs and that structured fields do not carry.

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 trigger condition and examples, then limits, return shape, cost and parameter scoping. It is dense and slightly wall-of-text, with parameter guidance packed into the same paragraph, but nearly every sentence carries information an agent needs, so little is wasted.

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?

Even though an output schema exists, the description pre-summarizes the returns (translated SRT/VTT with original times, dub script with max_chars and fit values), covers limits, cost, rights gating and rare parameters. Nothing an agent needs to invoke 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 coverage is already 100%, so the baseline is 3, but the description adds relational meaning the schema cannot: it ties subtitles to source_lang and confirm_rights true, clarifies target_lang is always required, and scopes library_id to only when transcribe_media returned one. It explains how include interacts with the over-long-line trimming.

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 (translate subtitles, produce a dub script) and anchors it with concrete user phrasings. It also implicitly distinguishes itself from the sibling transcribe_media by explaining that it consumes a transcript_id or SRT/VTT text rather than producing the transcript.

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?

Explicitly says when to use it (user wants captions or a spoken script in another language) with example utterances. It routes between input modes — pass transcript_id from transcribe_media or owned SRT/VTT text with source_lang — and states the confirm_rights precondition (only after the user says they own the recording).

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