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

Annotations already declare readOnly/idempotent/non-destructive, so the description wisely spends its words elsewhere: it discloses the x402 price and chains ($0.35 USDC on Base or Solana) and the external data dependency (Optimal Blue locked-rate index) that justifies openWorldHint. It does not say what happens when new_rate is omitted but credit_score/ltv are also absent — a real behavioral gap for a fallback path.

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?

Two sentences, front-loaded with the decision question and with the output list compressed into one readable clause; the pricing caveat is correctly demoted to its own line. Slightly dense with the comma-separated output enumeration, but nothing is redundant.

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 no output schema, the description carries its weight by naming all five return fields and the three verdict values, so the agent knows what it gets back. The remaining gap is the fallback path's dependency on credit_score/ltv and how the verdict thresholds are derived — acceptable omissions for a read-only calculator.

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% and each parameter already carries units, ranges and defaults (including the 2%-of-balance closing cost default), so the schema does the heavy lifting. The description adds only two things beyond it: the meaning of omitting new_rate and the interpretation of years_in_home as expected holding period.

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?

Opens with a concrete decision question ("Should this borrower refinance?") and immediately names the required inputs and the full set of computed outputs (payment, savings, break-even, net benefit, verdict). An agent can tell this apart from grade_mortgage_offer or get_bundle_refi_signal because it is a per-borrower scenario calculation, not a market signal or offer score.

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?

States the framing inputs ("Give the current rate, balance and years remaining") and the one mode switch that matters: omit new_rate to fall back to market rate. No explicit exclusions or sibling alternatives are named, so the agent must infer that bundle_refi_signal is the market-level alternative rather than a per-borrower scenario.

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