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

Annotations already declare destructive=true and idempotent=true, so the safety profile is partly covered. The description adds genuinely new context beyond structured fields: revision checking for concurrency, dryRun defaulting to preview, and that the saved action is undoable. It does not state what happens on a revision mismatch or the batch size cap implied by the schema.

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?

Three tight sentences with the mutation and its caption side effect front-loaded, followed by revision/dry-run behavior and the undo guarantee. No filler or redundancy; every clause carries 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?

An output schema exists so return values need not be described, and annotations cover safety. The description rounds this out with reversibility, revision control, and dry-run behavior. The only gaps are revision-mismatch handling and idempotency-key semantics for a 7-parameter destructive tool.

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 14% (essentially just 'projectId: UUID string'), so the description carries most of the burden. It adds meaning for three params, removeAssociatedCaptions (conditional caption removal), dryRun (previews by default), and expectedRevision (revision checked), but leaves itemIds, workspaceId, and idempotencyKey semantics unmentioned.

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 ('Remove selected timeline items') plus a scoped side effect ('their linked captions'), so the core operation is unambiguous. However, it never differentiates itself from the sibling 'delete_timeline_items', which an agent could easily confuse with this tool.

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?

The mention that 'dryRun previews by default' implies a preview-then-commit workflow, which is lightweight usage guidance. But there is no explicit when-to-use, when-not-to-use, or alternative (e.g., 'delete_timeline_items' or 'editor_edit_undo') named, so the agent must infer routing.

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