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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, openWorld; the description adds genuinely new context: the $0.002 USDC x402/Solana payment per successful call and an HTTPS endpoint equivalent, plus the default 28/36 DTI assumptions and the PMI-below-20%-down rule. Return content is characterized at a high level ('full monthly PITI breakdown') but no error/edge behavior or scheme details are given, keeping it at 4.

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 core question and outputs, then the alternate mode, then cost/transport. Each sentence does work, though the pricing and URL sentence is somewhat promotional and could be trimmed for a pure decision-making read.

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 12-parameter, no-output-schema financial calculator, the description covers the two usage modes, the constraint model (front/back-end DTI), the components of the returned PITI figure, and the payment/transport mechanics. It does not spell out the returned object's fields or units, which leaves a modest gap but is largely adequate.

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?

With only 50% schema description coverage across 12 parameters, the description carries real weight: it explains what annualIncome, monthlyDebts, downPayment, ratePct, frontEnd/backEndDtiPct (default 28/36), propertyTaxPct, insurancePerYear, hoaPerMonth, pmiPct and the homePrice mode flag mean in the computation. Only termYears and pmiPct's exact default go unmentioned in prose, so it meaningfully exceeds the schema-only baseline of 3.

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+resource ('How much house can I afford: maximum home price and loan') and enumerates the input drivers (income, monthly debts, down payment, rate) and the DTI constraint basis. It also distinguishes the two computational modes, so an agent can tell it apart from adjacent finance tools like loan_amortization or compound_interest.

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?

Explicitly states the mode switch: omit homePrice to solve for maximum affordability, or 'Give homePrice instead to get the monthly cost and the income needed.' That is clear conditional guidance. It stops short of naming named alternatives or exclusions (e.g. when to prefer loan_amortization for a fixed-schedule breakdown), so not a 5.

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