Sum up invoices and payments for a period

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description still adds real behavioral detail beyond them: cancelled and expired invoices are excluded from invoicedUsd, receivedUsd counts only confirmed payments that passed sanctions screening, multi-store calls return one summary per store plus a total, and failures arrive as coded errors such as rate_limited with a wait time. The only shortfall is that it doesn't note pagination-free limits on result size or currency handling, but the aggregation semantics are unusually well disclosed.

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?

Content is front-loaded: purpose, then output shape, then parameter mechanics, then the sibling pointer and error behavior. It is dense rather than padded, but a couple of sentences are long compound constructions that could be split for faster scanning.

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?

There is no output schema, yet the description specifies the aggregated fields returned (status counts, invoicedUsd, receivedUsd, per-network and per-token amounts), the multi-store return shape, and error signaling. For a read-only aggregate with a fully documented schema, nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so all four parameters are already documented; the description nonetheless adds meaning the schema does not encode, notably that period and createdFrom/createdTo are alternatives, that days are UTC, that a range is capped at 92 days, and that omitting store yields per-store summaries plus a total. It stops short of clarifying what happens if both period and dates are supplied or if only one date is given.

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 opens with a specific verb and resource ('Sums up the invoices created in a period') and immediately names the return shape: counts per status, invoicedUsd, receivedUsd, and per-network/token money. It also explicitly contrasts itself with the sibling list_invoices ('instead of paging through'), so the agent can separate it from that tool without reading either 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?

It states when to use this tool versus list_invoices ('Use list_invoices to see the invoices themselves'), how to supply the range (period enum or createdFrom+createdTo), the 92-day cap and the workaround ('ask for a year in four quarters'), and what happens with multiple stores. That is explicit when/when-not/alternative guidance, not implied.

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