reconstructed_trial_balance

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

Annotations already cover read-only/idempotent/non-destructive, but the description goes well beyond them: it discloses the underlying data source, that balance sheet accounts are cumulative while P&L accounts span period_start..as_at, that earlier P&L is collapsed into one prior-periods line, and that the output includes a debit=credit check. This is exactly the behavioral context a derived report needs.

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, leading with the tool's identity before the computation rules. The semicolon-chained clauses risk a run-on, but nearly every clause carries distinct, useful information rather than padding.

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?

An output schema exists, so return values need not be explained, and the description supplies the essential computation semantics, the non-authoritative caveat, and the debit/credit verification note. Minor omissions remain (accepted date format, whether as_at is inclusive), but the agent has enough to call it correctly.

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 must carry the load, and it largely does: as_at defines the balance date, and period_start is described with its default (1 Jan of the as_at year, flagged as an assumption) plus how it scopes P&L accounts. It does not specify date string formats or inclusivity, leaving a modest gap.

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?

Starts with a specific verb and resource ('RECONSTRUCTED trial balance from the /transactions ledger as at a date') and explicitly contrasts itself with the sibling trial_balance ('not Manager's Trial Balance'). An agent can distinguish it from both trial_balance and the other reconstructed_* tools without opening another 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 'authoritative: false; not Manager's Trial Balance' clause gives clear context for when this tool is the right pick (a derived, non-authoritative view) and implicitly routes to the authoritative alternative. It lacks an explicit 'use this when / not when' statement, so it falls short of full 5-level routing.

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