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

Annotations only tell us it is not read-only, not destructive and not open-world; the description adds real substance: the batch is atomic, each call writes a new revision, the exact undo path, the role of idempotencyKey/expectedRevision, the echo summary-vs-document return behavior, and beta account/quota context. That is well beyond the annotation surface and consistent with destructiveHint=false (edits are versioned and reversible).

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 core action is front-loaded, but the paragraph is a dense run-on that welds together schema guidance, undo routing, echo behavior, and a long beta/export-quota clause. The tier and export-count detail is tangential to invoking the edit and dilutes the actionable content.

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 mutating, multi-param tool with no output schema and thin annotations, the description covers return shape (project summary), reversibility, idempotency, and where to find the per-operation schema. The main gap is what happens on an expectedRevision conflict, which an agent needs before retrying.

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 coverage is only 40%, so the description must compensate and largely does: it explains operations[] as typed JSON objects with concrete type prefixes and clarifies echo=document versus the default summary. expectedRevision and idempotencyKey are named but their conflict/retry semantics are not spelled out, so it stops short of full coverage.

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 ('atomically apply a typed edit batch') and enumerates the operation families it accepts (scene.*/layer.*/audio.*/sfx.*/project.*/brand.apply/look.*). It also names adjacent tools (video_project_write for undo, video_projects action=get, video_edit_validate implied by the batch/validate split), so an agent can place it in the 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?

Gives clear routing: use video_project_write action=undo to reverse, video_projects action=get to read the document, and call video_guide first for the schema catalog. It does not explicitly state when to prefer video_edit_validate before applying, leaving that one comparison to inference.

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