Post-production edit

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

Annotations are all-false flags (not read-only, not idempotent, not destructive), so the description carries most of the burden. It adds meaningful context: the operation returns a NEW video and leaves the original untouched (consistent with destructiveHint=false, and it creates output consistent with readOnlyHint=false), discloses flat cost (~2 credits), fast execution, and the explicit non-AI, non-generative nature. It does not cover failure modes, auth requirements, or delivery of the resulting video URL.

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 key distinguishing info is front-loaded ('MECHANICAL post-production on an EXISTING rendered video... NO AI model'), and every sentence carries information. However, it is one dense, run-on paragraph combining operations list, constraints, brand behavior, cost, and exclusions. Splitting the ops inventory from the routing/negative guidance would improve scannability, though nothing 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?

For a medium-complexity tool with 5 params fully described in the schema and no output schema, the description is fairly complete: input type (served mp4 URL), operations available, ordering/cap semantics, cost, brand override behavior, and the fact that it returns a new video. It could note how the new video is surfaced, but the bare 'returns a NEW video' plus 'get_job' sibling availability covers most agent needs.

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 some value on top: the ops are 'applied in order' with a 6-op cap (cap also in schema), and brand params (name/domain/logo/accent) auto-load from the workspace with per-call override. It explains the append_card behavior the schema partly implies. This is helpful, but it does not compensate for any missing schema coverage since none is missing.

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 first clause nails it: 'MECHANICAL post-production on an EXISTING rendered video (its served mp4 URL)' — specific verb, resource, and scope. It lists the exact whitelisted primitives (trim, speed, mute, audio_gain, fade_out, append_card, watermark, grain) and actively differentiates from generative siblings like generate_video and render_ad. An agent can immediately tell this from the video-rendering tools in the sibling list.

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 clearly defines the lane ('The lane for: append a branded end card...') with concrete example phrasing and gives an explicit negative rule: 'NEVER use generate_video/render_ad for these mechanical asks.' It does not, however, enumerate the closest mechanical cousins in the sibling list (edit_video, reframe_video, upscale_video) or state conditions that would route to them, so differentiation from those is left implicit rather than explicit.

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