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

Annotations already mark it non-read-only, idempotent, and non-destructive, but the description adds substantial behavior: Studio-equivalent ownership/upload/timeline/quality/watermark checks, refusal of held last pictures with a named fix, reuse of current exports or running jobs, and queued-vs-finished semantics. No annotation contradiction is present.

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 front-loaded with purpose, then parameters, then checks/refusals, then the export-to-delivery workflow. It is dense but every sentence carries operational information, including the important idempotency and queued-job caveats.

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 complex export tool with no output schema, it covers the trigger, required inputs, validation checks, idempotent reuse, queued-job handling, and required delivery step. The main remaining gap is that the exact return shape is only implied by 'running job' and the download-link instruction, not explicitly described.

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%, so the description must carry parameter meaning. It names both required parameters and adds that project_id must be explicit and edl_version must be the reviewed version, but it does not explain acceptable edl_version values, how to obtain the reviewed version, or what happens with stale versions.

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, resource, format, and scope: export a reviewed edit as a full-resolution MP4 when the user asks for the finished video. This distinguishes it from preview/rendering tools and from delivery tools without requiring schema inspection.

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?

Gives an explicit trigger (user asks for the finished video), requires explicit project_id and reviewed edl_version, and explains the follow-up path: call wait_for_job, then download_url(kind='final', edl_version=...). It also handles repeated requests and warns never to claim delivery before a download link is returned.

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