PAID, $1.00: confirmed commercial mortgage maturities for one state

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

Goes well beyond the annotations: it discloses the payment/credential requirement as the only priced tool on the server, explains that quoting never charges, that the max_price_usd ceiling is checked before charging ('refused rather than charged'), and that the identical call is resubmitted for the paid path, reinforcing the idempotentHint. The readOnlyHint and destructiveHint are not contradicted; the description actually strengthens them by describing a read-only, non-destructive return with no mutation of domain data.

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 description is well sectioned by topic (returns, data quality, quoting, charging, free alternative) and every section carries distinct meaning, but it is bloated with repeated all-caps emphasis (the paid/credential point is hammered across multiple sentences: 'ONLY priced tool', 'ONLY THING THAT NEEDS A CREDENTIAL', 'the handshake's no signup is about the free tier', 'Everything else here needs no account at all'). It is informative but not tight; roughly a third of the words re-drive the same paid-vs-free distinction.

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?

Given the absence of an output schema and the presence of a nested authorize object plus a payment flow, the description fills the gaps: it enumerates the returned fields, explains the quote-to-authorization transition, states the data-population guarantee (19,881 confirmed loans, none estimated), and covers credential acquisition and the free fallback. Error handling and exact response shape are not specified, but the essential context for a correct call is fully provided.

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% for all four parameters and the nested authorize object, so the baseline is already high. The description adds marginal value on top, reinforcing that state drives pricing ('priced per state'), that limit does not affect price, and that authorize toggles quote vs. paid execution — but most of this is already stated in the schema descriptions, so the added semantic load is small.

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 the verb ('Returns'), the resource (LOANs, explicitly contrasted with events), the exact scope (one US state, one forward window, up to 200 loans), and the precise field list (maturity date, original principal, lender, instrument, origination date, property address). It also names the sibling tool it is not (search_property_events for events), so an agent can disambiguate 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 two-mode usage flow: omit authorize for a free quote, resend with authorize plus X-DFX-Account to be charged and served. It names the exact free alternative (search_property_events with event_type=LOAN_MATURITY_SCHEDULED) and gives the decision rule ('Use the free tool for timing, this one for a refinancing conversation'), plus the population difference driving that choice. It also clarifies who needs a credential (only this tool) and how to get one (open_dfx_account), so nothing 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.