Zovo Sales Payout Summary

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description still adds real value: it discloses that output is identical in shape to summarize_payouts minus Excel/PDF downloads, and it fences off capabilities an agent might otherwise assume (currency conversion, account linking, tax advice). The phrase 'does not need files' is potentially confusing next to a tool that accepts file and files inputs, which keeps this short of a 5.

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?

Single well-ordered paragraph: trigger with examples first, then the sibling alternative, then negative scope. Dense but every clause carries routing weight; the ambiguous 'does not need files' phrasing is the one sentence that doesn't land cleanly.

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 read-only aggregation tool with a rich schema, full annotation coverage and an output schema, the description covers everything an agent needs: inputs accepted, output shape by reference to the sibling, and boundaries. No return-value documentation is required since the output schema exists.

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% with self-documenting fields, so the baseline is 3. The description reinforces a few semantics (per-currency separation, the 1099-K/year framing, combined exports) but adds no new syntax or constraint detail beyond what the schema already spells out.

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 (compute monthly sales totals from an export or pasted rows), enumerates the supported platforms, and names the exact sibling it is not (summarize_payouts for spreadsheet/PDF output). An agent can route between the two without opening either 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?

Gives an explicit trigger ('when the user wants quick monthly sales totals ... and does not need files'), paraphrases real user utterances, names the alternative and the condition that selects it, and lists three exclusions (no account connection, no currency conversion, no tax advice).

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

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description goes well past them: platform auto-detection from headers, totals reconciliation against the export's Net column with residual, smallest-currency-unit output, and combination of multiple exports. It also states the defensible limits (no conversion, no advice), which is behavior an agent needs before promising results.

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?

Front-loaded with the trigger sentence, then capabilities, then exclusions, which is the right order. The two sentences are long and the output enumeration is dense, but nearly every clause (residual check, 1099-K view, workbook tabs) tells the agent something usable.

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 zero-required-parameter tool with nested file objects and an output schema, the description still covers inputs used, detection behavior, reconciliation, and the shape of the deliverables. Nothing needed to call it correctly appears to be missing.

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 still adds meaning: that several exports can be combined into one summary, that a year filter supports a 1099-K check, and that currency is only a fallback because in-file currencies win. It doesn't restate the file/transactions/enum details already in the schema.

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 description opens with a specific verb-plus-resource ('summarize' an attached Stripe/PayPal/Shopify/Etsy/Gumroad/Square export) and names exactly what comes back (per-month, per-currency gross/refunds/chargebacks/fees/net/payouts). An agent can tell this apart from a generic totals tool without opening the 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?

It gives a clear 'use this when' trigger list (bookkeeping, taxes, 1099-K check, PayPal history to Excel) plus explicit exclusions (no account connections, no PDFs or screenshots, no currency conversion, no tax advice). The sibling calculate_monthly_totals is never mentioned, so alternative routing 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.