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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds genuinely new behavioral facts on top: the input must be a complete permutation (no missing or extra ids), fields omitted from `underTitle` fall back into the body, and `[]` clears the line. It does not say what happens to the layout if the permutation check fails (rejection vs partial apply), which is the one gap for a destructive operation.

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-loaded with the core contract (full ordered id list, permutation requirement) before the derived-intent recipe and the edge cases. Information density is high with no filler, though the closing fragment 'A form is refused' reads slightly clipped and the optionality sentence could be tightened.

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?

With an output schema present, the description needn't explain returns, and it covers the risky parts an agent must know: permutation validation, prerequisite read, underTitle overflow semantics, and the form exclusion. The remaining hole is `peekId` — the description never states what it identifies or what happens when it is omitted, which matters given required parameters are zero.

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%, so the description must carry all parameter meaning, and it does well for two of three: `orderedItemIds` (full permutation) and `underTitle` (item ids in order, at most 4 short fields, `[]` empties). However `peekId` is never mentioned at all, despite being the identifier that selects the layout, and the note that '`orderedItemIds` is optional with `underTitle`' is ambiguous about the exact interaction.

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 ('Reorder a record layout's ... items') plus the mechanism ('passing the full list of item ids in the desired order'), which immediately separates it from peek.add_layout_item, peek.remove_layout_item, and item_tree.move. It also carves out the form case explicitly ('A form is refused: reorder its questions with form.update `order`'), so the resource boundary is unambiguous.

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 an explicit prerequisite ('call peek.read first to discover ids') and translates common intents into the required action ('For "move X to top" or "put Y after Z", read the layout, build the new id sequence yourself, and pass it here'). It also names the correct alternative tool for the form case, so both when-to-use and when-not-to-use are covered.

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