Move energy flow positions

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

With no annotations, the description carries the full burden, and it does disclose real behavior: the whole call is a single undoable step and changes are not persisted until save. It omits what is returned, whether dx/dy default to zero when omitted (they are not required), and what happens if a referenced feature or flow index does not exist.

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 short sentences, front-loaded with the action and offsets, followed by the pairing caveat and the persistence caveat. Minimal waste, though the phrase 'the car picture' is slightly opaque for an agent that has never seen this file model.

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 mutation tool with no annotations, no output schema and 0% schema coverage, the description covers the essentials: what moves, the offsets, undo granularity, and the save requirement. The remaining gaps (return value, index semantics, omitted-offset behavior) are notable but not fatal for a move operation.

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 description coverage is 0% across three parameters, so the description must compensate. It names the three item kinds (car, feature, flow) that correspond to the items union, but leaves the integer values for feature/flow unexplained (index? id?) and gives no units or sign convention for dx/dy beyond 'by dx / dy'.

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 gives a concrete verb (moves) plus the addressed resource (the car picture, features or flows of the energy flow file), and the dx/dy offsets tie it to the input schema. It implicitly scopes itself to energy-flow content, which separates it from generic siblings like move_items and move_parking, but it never names those alternatives explicitly.

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 line 'A track and its mask usually move together' is genuine usage guidance about how to select items, and '(one undo step)' hints at batching intent. However, there is no when-to-use / when-not guidance relative to move_items, move_parking or align_items, so an agent must infer which mover to pick.

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