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

Annotations only give readOnlyHint=false/destructiveHint=false/openWorldHint=false; the description goes well beyond by disclosing the success condition (job succeeds only when the stream holds every planned frame), how duration is obtained (probed from the file), where rendering happens (private engine), where the MP4 lands (AMZ Vault, never published), and account-tier quota limits for the beta.

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 start action and its parameters, then cancel/retry, then behavioral notes — a sensible order. It is dense and long, and the tier/quota details slightly duplicate the 'call video_guide for tier notes' instruction, but nearly every sentence carries actionable information.

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?

No output schema exists, yet the description explains what start returns (a job to poll with video_jobs) and what result.duration means, and it covers engine behavior, storage location, and account-tier limits. For a beta mutation tool this is complete enough to invoke correctly.

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 0% and the schema only exposes four properties, so the description carries the full burden — and it does: it maps action-specific parameters (projectId, expectedRevision, idempotencyKey, jobId, kind, startFrame/endFrame), gives the kind enum semantics (frame|contact|preview|export), and explains that startFrame/endFrame only apply to preview, not export.

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 (Video Director render) and enumerates the three actions (start, cancel, retry) with the parameters each takes. It also names the related siblings video_jobs (polling) and video_guide (catalog), so an agent can distinguish it from the rest of the video_* family without opening a 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?

Explicit routing: use start to render, cancel/retry with the given params, and an explicit when-not/alternative — 'An export always covers the whole project; to test a range, render kind=preview with startFrame/endFrame.' It also directs the agent to call video_guide first, which is a concrete prerequisite.

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