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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: 'add true' preserves the existing output, frame null restores the original shape, unsupported changes refuse without rebuilding, retries must reuse operation_id, and the edit draws on the account's direct-edit allowance at no cost. That is exactly the behavioral detail the annotations cannot express.

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 core action and the ratio enum, and nearly every clause carries unique information. The semicolon-chained, telegraphic style ('subject follows the subject') is slightly harder to parse and could be broken into clearer sentences without losing density.

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?

An output schema exists so return values need not be described, and the description still covers prerequisites, mutation semantics, error/refusal behavior, retry protocol, cost, and the follow-up download path. Nothing an agent needs to call this destructive write correctly is missing.

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?

With 67% schema coverage, the description still adds meaning the schema cannot: it explains fit modes (subject follows subject, contain adds bars, cover fills with optional x/y), that frame=null restores the original, and that add=true branches a new output. It also ties base_version/output_id to get_project_context and explains operation_id retry semantics.

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?

Opens with a specific verb and resource plus the exact set of allowed ratios, so the agent knows precisely what changes. It is distinguishable from siblings such as edit_video, revise_video, and check_video because it is scoped to output framing only.

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 explicit prerequisites (read get_project_context first and pass its base_version and output_id), an explicit exclusion ('Crop only when requested'), and routes file retrieval to a different tool ('request a file separately with check_video with_download'). When-to-use and when-not-to-use are both covered.

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