Item (destructive)

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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds the crucial non-obvious behavior: the first call only returns a plan and confirm_token, and the call must be repeated with the token to actually apply. That is real context beyond the structured fields; it could still say more about reversibility/snapshot policy defaults.

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-loads the verb and action list, then the invocation sequence, then the batching hint — every line earns its place. The telegram-style abbreviation ('item*', bare param lists) is terse but not padded.

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 destructive, nested-schema tool this covers the essentials: destructive nature (via annotations), the plan/confirm flow, dry_run and snapshot (documented in schema), and where to route batches. An output schema exists so return values need no explanation; only snapshot server-policy defaults and irreversibility go unstated.

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?

The schema's `op` object is a free-form additionalProperties bag with only the action enum, so the description carries the per-action parameter contract: required markers on item/frame, 'All' as a valid color value, and the 1-based index for delete_take. Without this text the parameters would be unusable.

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 ('Remove') plus the resource ('item objects') and enumerates exactly the two sub-actions (delete_item_markers, delete_take), so an agent can tell this apart from sibling deleters like media_delete or timeline_delete. It does not explicitly contrast with item_write, which keeps 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?

Gives concrete routing guidance: use ONE batch_run when the calls are known in advance / the same change applies to several items, and documents the two-phase plan+confirm_token invocation pattern. It stops short of saying when to prefer this over item_write or a full timeline_delete.

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