qb_deposit

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

Annotations declare this is a non-idempotent write that is not destructive, and the description adds real value beyond that: the two-step preview/confirm_code protocol, the fact that payment lines have their amount looked up server-side and folded into total and expected_total, and the currency/exchange_rate convention. It stops short of saying what the preview call actually returns (e.g. the confirm code itself) or what happens on a second confirm with the same code, which matters given idempotentHint=false.

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 critical fact — this is a money-in deposit with two line shapes — is front-loaded, and the parenthetical glosses (e.g. 'no "amount": it is the payment's own amount') are economical. The line-wrapped prose around exchange_rate is slightly dense but no sentence is filler.

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 10-parameter, non-idempotent mutation with no output schema, the description covers the domain semantics well but leaves the agent guessing about the mechanics of the confirm step: how the confirm_code is obtained, whether the preview call has a side effect, and what expected_total validation does on mismatch. Those are the gaps an agent is most likely to trip on.

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 is doing all the work — and it covers the hardest parts well: the two mutually exclusive line shapes, that payment_txn_id lines omit 'amount', the 'entity' and 'memo' fields, the currency of amounts, and the direction of exchange_rate ('home-currency units per 1 unit of that currency'). It leaves confirm_code, run_id, expected_company_file, and deposit_to_account undefined, which keeps it out of the top score.

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 line gives a concrete verb+resource ('Money into a bank account (Make Deposits)') and names the QuickBooks construct, so an agent immediately knows this creates a deposit transaction. It does not explicitly contrast itself with the closest sibling, qb_receive_payment, which is the main ambiguity an agent would have to resolve on its own.

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?

Usage is implied rather than stated: the 'payment_txn_id — a received payment sitting in Undeposited Funds' branch tells the agent this is the step that follows qb_receive_payment, but the description never says 'use this instead of X when Y'. There is no explicit when-not guidance and no mention of prerequisites such as a closed period or the need for the target account to exist.

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