Audit PO vs Receiving vs Supplier Invoice (3-Way Match + QuickBooks/Xero CSVs)

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds real behavior: determinism, the four specific mismatch classes detected, the two CSV export targets, the debit-memo artifact, and the 15-line free-tier cap. One ambiguity: 'Emits ... a vendor Debit Memo email' could read as an outbound send under readOnlyHint=true, though 'Emits' most plausibly means generated as output — worth clarifying but not a hard contradiction.

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?

Four sentences, front-loaded with the engine's purpose and backed by concrete audit targets and outputs; the paywall/quota sentence sits last where it belongs. Slight marketing padding ('Deterministic Finance Ops', 'silent unit-price creep') costs a point but nothing is buried.

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 14 parameters but 100% schema description coverage and no output schema, the description carries its weight by describing exactly what is returned (QuickBooks and Xero bill CSVs with verified quantities/costs, plus a debit memo) and the quota limit. It leaves demo_mode, date defaults, and failure behavior to the schema, which is acceptable but not complete.

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, and the description goes beyond it by tying business concepts to specific parameters — damaged vs good receiving units, freight cap overages (agreed_freight_cap_usd), unapproved surcharges (invoice_extra_fees_usd), and dual accounting exports. It still doesn't explain defaults like demo_mode or the date/currency conventions, so it improves on the schema without fully replacing it.

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 chain and the exact three data sources it reconciles (approved PO lines, dock receiving counts split good/damaged, billed invoice lines), plus the artifacts produced. This is clearly distinguishable from the sibling tools (replenishment planning, PO building, CSV migration), so an agent can route here for audit work without opening any 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?

Usage context is implied by 'for wholesalers and Shopify merchants' and by naming the audit scenarios (price creep, short-shipments, surcharges, freight caps), but there is no explicit 'use this when / not when' statement and no reference to the sibling tools as alternatives. The only explicit condition is a licensing/quota note, which is not selection guidance.

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