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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=false) by disclosing that the edit is saved as an undoable version, that the clip's video is replaced by a new render, and that it costs no Horizon Units. It also describes the post-call workflow (job_id, poll job_status, then preview_frame), which is the key behavioral consequence for an asynchronous mutation.

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 when-to-use intent before parameter detail and excludes non-targets, so it reads in the right order. It is a dense single block, though, and the four parameter groups would scan faster as separate lines; the quoted example phrases earn their space but add length.

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 a 23-parameter mutating tool with an output schema, the description covers the missing pieces: per-mode parameter meaning, side effects, cost, and the follow-up polling path. An agent has everything needed to select the tool, build arguments for the intended mode, and handle the async result.

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 23 parameters and 0% schema description coverage, the description carries the full burden and largely succeeds: it groups parameters by mode (text, sticker, sound, B-roll), gives positional enums (top/middle/bottom, top/bottom layout), concrete value examples (neon/gradient/3D, title/lower third/subscribe), and default semantics such as text_end_seconds 0 meaning 3 s and broll_seconds 1.5-8. Remaining gaps are minor (no numeric ranges for text_size/sticker_size, and sticker_seconds is described as defaulting to 2 while the schema default is null).

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 precise verb and resource set (put text, a sticker, a sound or B-roll on a clip) and grounds it in concrete user phrasings. It explicitly distinguishes this from siblings that handle captions, music, and translated subtitles, so an agent can route correctly without opening other schemas.

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?

Provides both positive triggers (quoted user intents for titles, emoji stickers, whooshes, B-roll) and an explicit 'Not for' list naming style_clip, edit_clip, and translate_captions as the correct alternatives. It also states that B-roll must be requested in a call of its own, which is a usage constraint that changes how the agent batches calls.

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