object.delete

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

Annotations already mark the operation as write, destructive, and idempotent. The description adds meaningful context beyond those annotations: unlinking happens immediately, rollback restores it, and commit removes the data-block. It also suggests an unselected-object precondition, and it does not contradict any annotation.

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 a single compact sentence and front-loads the core verb (`Unlink`). There is no wasted wording, though the three-way temporal clause (`now`, `rollback`, `when the structural transaction commits`) is slightly hard to parse.

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?

The high parameter count, guard fields, and transaction semantics require more context than the description provides. It does not explain how identity and scene-generation checks work, what idempotency means here, or how `transaction_id` relates to `transaction.begin`/`transaction.commit`, so it is incomplete for correct invocation.

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 0% schema description coverage and five required parameters, the description should carry parameter meaning. It only gestures at `object` and transaction timing; `expected_object_identity`, `expected_scene_generation`, and `idempotency_key` are left undocumented, so an agent cannot reliably know how to fill them correctly.

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?

The description identifies a concrete action (`unlink` / `remove the object data-block`) on a specific resource (`one exact unselected object`). It reads as a deletion/unlink tool and is distinguishable from siblings like `object.duplicate`, `object.set`, or `object.transform`, though the `unselected` requirement is somewhat opaque.

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 transactional wording (`restore it on rollback`, `when the structural transaction commits`) implies the intended context is inside a transaction, but there is no explicit direction about when to choose this over alternatives or how transaction lifecycle functions relate. Usage guidance is present only by implication.

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