New Item

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

Annotations already mark this as non-read-only, and the description adds meaningful side-effect details: the sidecar is created if absent, written back, and rev/lifecycle fields are seeded with held defaults rather than C1. It does not cover error or concurrency behavior, but it goes well beyond the structured annotations.

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 leads with the core operation, then a tight parameter list, then a one-line return shape. The only minor issue is the cryptic parenthetical '#141 state machine, not C1,' which is somewhat insider-specific but not disqualifying.

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?

Inputs, optionality, the side-effect of writing the registry, and the return shape are all covered, which is sufficient for invoking the tool despite the lack of an output schema. Missing duplicate-item behavior and exact part-number formatting are secondary gaps.

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 prose is the only source of parameter meaning. It explains registry as the sidecar path, item as the manifest-stable logical id, files as an optional artifact mapping list, and metadata as queryable free-form attributes—far exceeding the bare type/title schema.

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 opening sentence names a concrete action ('Allocate a non-significant sequential part number and register a new item') against a specific resource ('an items.json sidecar'), and adds behavior ('created if absent, writing it back'). This clearly separates it from item validation/resolution siblings like items_validate, items_resolve, and items_check_manifest.

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 description gives clear context: this tool is for creating a new item and registering it in the items registry, with 'new item' making the selection obvious. It does not explicitly name sibling alternatives or state when not to use it, but the creation intent is unmistakable.

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