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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description goes well beyond that with pricing ($0.40), the free-refusal contract (coverage_gap, no_charge), the shared 3-calls-per-IP-per-day quota, x402 fallback behavior when no api_key is passed, and the optional Ed25519 receipt with its verification path. These are real behavioral traits an agent cannot get from 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?

The content is dense and largely useful, but the opening token 'PAID ($0.40).' front-loads a payment status rather than the purpose, and the certified-extract disclaimer is repeated in both the description and the receipt parameter schema. The result is a wall of choppy sentences where the purpose sentence is buried after pricing metadata.

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 paid, open-world computation tool with a full output schema and complete param coverage, the description supplies the pricing, the refusal policy, the auth path, the quota, and the receipt/verification contract. It does not need to explain return values because an output schema exists, and nothing material to correct invocation appears 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. The description adds genuine meaning on top: the alternative input pattern (due_date OR invoice_date+terms_days), the as_of default of today, and the receipt flag's no-extra-cost semantics on paid successes. The only omission is that it does not explain debtor or currency expectations, which the schema covers only thinly.

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 states a specific outcome set: whether an invoice is overdue, by how many days, and the statutory late-payment interest owed (Actual/365 simple). It names the supported regime countries explicitly, which scopes the tool concretely. However, it never distinguishes itself from the sibling 'compute_statutory_interest', which appears to overlap on the interest-computation half of this tool's job.

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 tells the agent exactly what to supply ('Send due_date, or invoice_date with terms_days') and what happens when the answer is not achievable ('refused free (coverage_gap, no_charge)'). Payment context (api_key vs. x402, shared 3 free calls/IP/day) is spelled out. It stops short of naming an alternative tool when the invoice is outside the supported regimes.

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