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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only' adds nothing, but the description contributes genuinely new behavioral context: the 2026 pay-table data source (which bounds output validity) and an explicit PII constraint ('Do not send a name or SSN'). It still does not describe the response shape or any limits beyond that.

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?

Three tight sentences, front-loaded with what is computed and then the data source and safety note; no filler. It is close to optimally sized for a short description, though the parameter coverage gap suggests some budget could have been spent there instead of restating 'Read-only'.

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 13-parameter financial calculator with no output schema, the description establishes the domain and key inputs but omits what the result actually contains (monthly payment, price, income breakdown) and how the major optional levers (rate, maxDti, tax/insurance) shape the estimate. Annotations cover safety, so the remaining gap is about the assumptions and outputs of the calculation.

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 only 46% across 13 parameters, so the description is expected to compensate and does not. It names just three inputs (pay grade, years of service, dependents) and leaves rate, maxDti, downPayment, hoaMonthly, otherDebts, vaFirstUse, vaDisabilityExempt, insuranceMonthly, monthlyTaxOverride and propertyTaxRatePercent entirely unexplained in prose.

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?

Specific verb (estimate) plus a well-scoped resource: Honolulu County military income components (base pay, BAH, BAS, COLA) and a VA purchase price, with the data source named (RealityCents 2026 pay tables). It is clearly distinct in flavor from generic siblings like calculate_affordability, but it never explicitly names or rules out the closest alternative (calculate_affordability, va_remaining_entitlement), so sibling differentiation is left to inference.

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?

Usage is implied by the input framing ('from pay grade, years of service, and dependents') and the Honolulu/military scope, which tells an agent roughly when this applies. However there is no explicit when-to-use statement, no exclusion (e.g. vs calculate_affordability), and no prerequisites, so the agent must infer routing.

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