List receipts

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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuine behavioral context beyond those flags: Moneybird defaults to `period:this_year`, meaning a bare call does not return all receipts but only those in the current financial year, and the note that paid/late/pending_payment states only apply to purchase invoices and receipts. No contradiction with 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 purpose sentence is front-loaded, precise, and self-contained, and the filter key enumeration is directly useful to an agent reading only the description. Small deduction because the filter enumeration duplicates the schema's `filter` description nearly verbatim rather than contributing distinct structure, adding minor redundancy.

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?

The definition is complete for a list operation with rich annotations and 100% schema coverage: purpose, resource definition, filter semantics, pagination, and the critical period default are all available to an agent. The only gap is the absence of return-shape guidance, since there is no output schema, but the resource is well-defined and a get_receipt sibling exists for single-object detail.

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 100% and the schema's `filter` description is strictly more detailed than the description text, adding the pipe-combination rule and the Moneybird period default. The description merely enumerates the same filter keys without adding any new parameter meaning, so the baseline of 3 applies per the rubric.

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 ('List receipts') and immediately defines the resource in meaningful terms ('expenses paid on the spot, without a supplier invoice'). The parenthetical disambiguates receipts from purchase invoices, which matters given the sibling list_purchase_invoices. An agent can tell this tool apart without inspecting the schema.

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 definition of a receipt as an expense 'without a supplier invoice' provides a clear selection condition: if the expense has a supplier invoice, an agent should look to purchase invoices instead. However, it never names an alternative tool explicitly (e.g., list_purchase_invoices) and contains no when-not statement, so it falls just short of explicit routing guidance.

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