ledger_transactions

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

Annotations already cover read-only/idempotent/destructive status, and the description adds genuinely non-obvious behavior: Manager ignores dates on this endpoint so from_date/to_date are filtered client-side, the full ledger is fetched, and completeness is reported. The default/max pagination bounds (500/5000) are additional operational detail not in the structured fields.

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?

Dense but front-loaded: source/scope first, then date-filter caveat, then pagination, then exclusions. Every sentence carries information; it is packed but not padded.

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?

With an output schema present, return-value explanation is unnecessary, and the description covers fetch/completeness behavior and the client-side date filtering. The remaining gap is explicit mapping of the 11 filter parameters, which is partly implied by the field enumeration but not stated.

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 0%, so the description carries the burden. It adds date format (YYYY-MM-DD), and skip/limit defaults and max, plus names the ledger fields (account, counterparty, tax, reference, bank_account, transaction_type) that likely correspond to filters, but it never explicitly states that account/customer/supplier/tax_only/reference are filter parameters, leaving half the semantics to inference.

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/resource: historical transaction data from the /transactions ledger, GET only. The closing exclusions ('Not a finished report; not an as-at balance') carve out clear boundaries against the sibling reconstructed/report tools, and the row-field enumeration (account, type, counterparty, tax, debit/credit, signed amount) makes the content concrete.

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?

Gives clear context: GET-only, raw ledger rather than a report or as-at balance, with pagination defaults. It does not explicitly route the agent between this tool and the similarly-named sibling account_ledger or general_ledger_summary, so it stops short of full when/when-not guidance.

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