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

Annotations only say read-only, idempotent, closed-world; the description adds the substance that matters: real CapCenter pricing, zero-closing-cost assumption with points shown, break-even months, total interest, a benefit horizon tied to years staying, a recommendation flag, and the explicit 'estimate, not a loan offer' disclaimer. It also discloses the Spanish-language behavior including that legal disclosures remain in English.

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?

Effectively one dense sentence plus a disclaimer and a language note; the output contents are front-loaded and every clause carries information. It is slightly run-on and could be split into a what-it-returns list for faster scanning.

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 13 parameters, no output schema, and a complex financial computation, the description does the work of explaining what comes back: new P&I, payment change, cost to close, break-even, total interest, and estimated benefit. The estimate disclaimer and language caveat close the remaining gaps.

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 description coverage is 100%, so the schema already explains all 13 parameters including the county slug format and the payment auto-derivation. The description adds only modest meaning, notably that years_staying drives the benefit horizon and that language=es switches the response language, so the baseline 3 applies.

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 (compare) and a precise resource set: keeping the current mortgage versus a rate-and-term refi, cash-out refi, and home equity loan, all on CapCenter pricing. That clearly separates it from siblings like explain_loan_options or get_mortgage_quote, which don't produce a side-by-side break-even analysis.

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 description makes the triggering scenario clear (an existing borrower weighing refinance/HELOC against staying put) and notes the tool will flag when keeping the current loan wins. It stops short of explicitly naming when to route to a sibling instead, but the context is unambiguous.

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