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

Beyond the annotations, the description discloses meaningful behavior: complete=false does not create a watchable complete preview, complete=true stores a complete video even on the first call, approval renders from the original at up to 720x1280 portrait, and report=true re-reads a stored report without rendering. It does not describe auth, rate limits, or failure modes, but it adds substantial operational context that annotations alone do not provide.

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 a dense run-on block with all-caps labels, nested caveats, and a long digression into verification advisories, picture checks, caption checks, and measures. Useful content is front-loaded only partially, and many clauses could be consolidated into clearer structured guidance.

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?

There is no output schema, and the description compensates by explaining what results include: verification advisories, PICTURE CHECK, CAPTION CHECK, MEASURES, PICTURE MEASURES, and retrieval via watch_video or download_url. For a complex render-and-inspect tool this is largely complete, though the missing sibling contrast and unclear defaults leave a small gap.

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 only 25%, so the description must carry most parameter meaning. It explains complete=false vs true, quality=approval vs draft and the implication that approval forces complete=true, report=true as a stored-report read, and reinforces that project_id is the immutable scope. That compensates well for the thin schema, though default values are not stated.

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 states the core action: it renders evidence for the current immutable EDL, and it distinguishes complete=false changed-section proof from complete=true full stored video. That is a clear verb and resource, though the dense opening and lack of explicit contrast with siblings like render_variants or export_final keep it from a 5.

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 actionable mode guidance: complete=false is only changed-section proof and not a watchable preview, complete=true creates the complete stored video, quality=approval implies complete=true, and draft is the inexpensive 480px option. It also explains wait_for_job and calling render_preview again to review an existing result, but it does not explicitly say when to prefer this over sibling rendering/export tools.

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