Create Itemized Expense

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

With no annotations, the description carries the burden and does well: it reveals that the tool computes each person's owed share in integer paise, reconciles to the total before writing, supports per-item split modes, and that dry_run avoids creating anything. This goes well beyond the bare input schema.

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 long but the embedded items structure is the clearest way to convey an inherently complex parameter. It is front-loaded with the core purpose and uses the inline JSON efficiently, though a few phrases could be trimmed.

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 complex tool with a free-form items schema, the description gives enough detail to construct valid calls, covering split modes, amount formats, and dry_run behavior. It does not discuss date formats or error conditions, but the output schema likely covers the return shape and the required fields are obvious.

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 compensates by fully documenting the complex items parameter, including amount formatting, split types, paid_by, and split_ref. It also explains dry_run. It does not describe date, currency_code, group_id, or description, though those are relatively self-explanatory.

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 states a specific action ('Create ONE Splitwise expense') on a specific resource, and qualifies it as being built from itemized line-items each with its own split. This clearly distinguishes it from the sibling create_expense tool, which handles a single split.

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?

It gives clear context: 'This is how a receipt becomes an expense' and explains that line-items are extracted from a receipt image and passed here. It also mentions dry_run for preview, but it does not explicitly state when to prefer this over create_expense or list exclusions.

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