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

Beyond the annotations (destructive=true, idempotent=true) it discloses that the clip's video is replaced by a new render, that the change is saved as an undoable version, that RipClip's own model is used, that a long clip takes a minute, and that it costs no Horizon Units — all decision-relevant facts not encoded anywhere in the structured fields. It also explains the async lifecycle: returns job_id, then poll job_status, then preview_frame, which is exactly the operational context an agent needs.

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 content is front-loaded with the trigger before parameters and exclusions, and nearly every clause carries new information (timing preservation, cost, job flow). It is dense and runs long for a three-parameter tool, with some mid-sentence line breaks that hurt scannability, but no sentence is truly redundant.

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?

For an async, destructive render job the description covers mutation consequences, reversibility, cost, latency, and the downstream job_status/preview_frame polling path; an output schema exists, so the return shape needs no further explanation. Nothing an agent needs in order to invoke this correctly and follow up 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 0%, so the description must carry all three parameters, and it does: clip_id sourced from list_clips, language accepting a name or code with enumerated examples plus the sentinel value 'off' to remove a translation, and mode contrasting 'bilingual (default)' against 'replace'. The sentinel value and default-mode semantics are genuinely non-obvious information that the bare schema does not convey.

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?

The description opens with a concrete verb+resource ('translate captions' / 'subtitles in another language on a clip') and illustrates it with real user phrasings ('add Spanish subtitles', 'translate it to Japanese'). It also names the adjacent-but-different siblings (style_clip, edit_clip for looks, write_captions implicitly for originals), so an agent can separate it from near-neighbours without opening any 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 gives an explicit trigger ('when the user wants subtitles in another language on a clip') backed by three example utterances, then an explicit 'Not for:' block excluding dubbing/voiceover and caption styling with the sibling to use instead. The when-to-use, when-not-to-use, and alternative routing are all stated rather than inferred.

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