trial_balance

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

Annotations only say read-only/non-destructive; the description goes well beyond them by disclosing the snapshot caching model, the refusal path ('listing_snapshot_changed' with its two causes), the up-to-10-minute staleness window, the exact ledger scoping rules (base_currency_ledgers_only, foreign_currency_ledgers_excluded, base_currency_ledgers_mixed_excluded) and that totals are not expected to balance. It also honestly discloses a side effect not visible in annotations: metadata-only receipt lines appended to a local log, while writing nothing to Tally.

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 core purpose is correctly front-loaded in sentence one, but the remainder is a single dense run-on paragraph with nested clauses and marginal detail ('a save with no change and a master change made in Tally's own screens each moved a mark when measured (protocol reference section 11c.5, one run each)'). Almost every sentence carries relevant information, but bullet points or paragraph breaks would make the snapshot protocol far easier to parse.

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 no output schema, the description carries the return-value burden and does a good job: it names the 'snapshot' fields (id, master_alter_id, voucher_alter_id, read_at, reused), the totals scope, and the row scoping. The detailed ledger row shape and the receipt-line format are not described, but the omissions are minor for a report endpoint.

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 the baseline is 3, but the description adds real semantics the schema lacks: snapshot_id must be the first page's id and is only meaningful on later pages, and its effect (refusal rather than silent continuation from a different report) is spelled out. It also explains the offset/limit pagination contract (a fresh report is captured at offset 0 and reused for later pages).

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 ('Return native ledger-wise Trial Balance for a date range') and adds the mechanism ('using Tally's TBAL fields without scanning vouchers'), which distinguishes it from voucher-scanning siblings. It also explicitly names the adjacent tool it is not (ledger_movement), so an agent can separate the two without opening schemas.

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 prerequisites ('Requires an INR base currency and supported date boundaries') and an explicit redirect with its selecting condition ('For one ledger's movement counted from the window's vouchers... use ledger_movement instead'). It does not, however, address close sibling reports such as balance_sheet, profit_and_loss or statement_tie_out, so routing for the wider report family is left to inference.

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