create_expense

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

No annotations are present, so the description carries the full disclosure burden. It only discloses that an expense is created and that categories is typed as string[] in the SDK. It does not state whether the expense is created in draft or published state (critical given the publish parameter and the publish_expense sibling), what happens on validation failure, whether creation is idempotent, or any multi-currency exchange-rate behavior.

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?

Two sentences with no filler, and the purpose claim is front-loaded. The categories caveat is explicitly flagged as an 'Assumption' rather than asserted, which is the right framing for a typing uncertainty. The brevity reflects under-specification, but that is penalized under contextual completeness rather than here.

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 financial creation tool with 11 parameters (9 required), no annotations, no output schema, and a largely bare schema, the description leaves an agent unable to invoke it confidently. Key gaps: the publish parameter's effect, draft-vs-published workflow (especially given publish_expense exists as a sibling), how categories strings map to real category objects, and the required interplay between currencyCode and exchangeRate. The description explains the what but none of the how or when.

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 only 18%, covering just categories and paymentDate. The description's categories note largely repeats the schema text ('SDK currently types categories as string[]'), adding no new semantics, and the other nine parameters — publish, currencyCode, exchangeRate, payeeId, branchId, paymentAccountId, attachments, referenceNo, description — receive no added meaning. The publish boolean's effect is entirely unexplained.

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 — 'Create an expense in Bigcapital' — which clearly names the operation and the domain. The sibling set contains create_bill, create_invoice, create_payment_received, and create_manual_journal, and the resource name 'expense' partially distinguishes this tool from them. However, it does not clarify the accounting boundary between an 'expense' and a 'bill', so sibling differentiation is only surface-level.

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?

No when-to-use guidance or exclusions are provided. With siblings like create_bill, create_manual_journal, and create_payment_received representing distinct accounting workflows, an agent gets no criteria for choosing this tool over those. The second sentence is a type assumption about categories, not usage context.

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