Edit a video clip

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

Annotations only set readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false. The description adds meaningful behavior: it preserves original motion/timing/edit, changes subject/setting/style; it is a paid render; and it returns the served URL of the edited clip. It also discloses the identity/product grounding behavior via the `elements` parameter. A small gap: it doesn't explicitly warn about whether the source clip is consumed or what happens to the audio if keepAudio is omitted, but the schema covers keepAudio default. The behavior about preserving motion/timing is important and disclosed.

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 description is dense but well-structured: the first sentence states the core transformation, followed by concrete examples, constraints, exclusions, and cost/return. It is longer than ideal, but every sentence adds value, and key behavioral information is front-loaded. The NOT list is long yet necessary for routing among many video sibling tools.

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?

Given the complexity (video-to-video transformation with optional grounding, audio toggle, paid render) and no output schema, the description covers the core semantics: what it does, constraints, alternatives, and return type (served URL). It doesn't detail failure modes (e.g., what if the video is too long or the instruction is ambiguous) or how the audio is handled when keepAudio is false in terms of output format, but given annotations and schema coverage, this is adequate and only missing minor edge-case guidance.

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 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: it explains the `elements` parameter's purpose ('so the edit restores the REAL thing instead of re-inventing it') and that `instruction` is in the user's own words, mapping to the natural-language behavior. It also adds context about the video source URL, tying it to 'a previous render, a job result, or list_library' – but that comes from the schema. The description reinforces the exact role of `instruction` and `elements` without redundancy, warranting a 4.

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 clearly states a specific verb and resource ('EDIT/transform an existing video clip with a natural-language instruction (video-to-video)'), and explicitly distinguishes itself from sibling tools like post_edit, generate_video, dub_video, recast_motion, and render_ad via concrete examples. The transformation scope is well-defined, including what it does NOT do, which makes it immediately distinguishable from related tools.

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?

The description provides explicit when-to-use guidance ('Use for...') with multiple concrete examples, and explicit when-not-to-use exclusions naming specific sibling tools (post_edit, generate_video/render_ad, dub_video, recast_motion). It also gives a practical constraint ('Best on 3–10s clips'), making it easy for an agent to route correctly.

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