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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes beyond them by disclosing the embedded business rules: 3.5% down at 580+, 1.75% UFMIP plus annual MIP, 3%/5% Conventional minimums at 620+, credit-tiered PMI, and PMI cancellation at 80%/78% LTV. That tells the agent what assumptions the output rests on, which is genuinely useful; it does not disclose response shape or units, but the annotations carry most of the remaining burden.

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?

It is a single front-loaded sentence that opens with the action and the two compared programs before the parenthetical detail, so the most important information comes first. The nested parentheses make it dense to parse, but no sentence is wasted.

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 analytical tool with no output schema, the description does state the key return values (5- and 10-year totals, exact crossover credit score), which is the main thing an agent needs. It stops short of noting the DTI comparison implied by grossMonthlyIncome or the role of holdingHorizonYears, leaving minor gaps in what the output will contain.

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% and every parameter carries a description with defaults and bounds, so the schema does the heavy lifting and the 3 baseline applies. The description adds modest value by tying the 3.5%/3%/5% down-payment and 580/620 credit figures to the comparison logic, but it does not individually explain parameters such as holdingHorizonYears or downPaymentMode beyond what the schema already states.

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 (compares) and two named resources (FHA vs Conventional), then states exactly what is returned: 5-year and 10-year total cost plus the credit score crossover point. That is clearly distinct from the sibling tools (affordability, DTI, down-payment assistance, readiness score), none of which produce a side-by-side loan-program cost comparison.

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 narrow scope: an agent can infer this is for borrowers choosing between FHA and Conventional. However, there is no explicit when-to-use framing, no mention of when a sibling such as calculate_mortgage_affordability or calculate_mortgage_dti would be the better call, and no stated prerequisites (e.g. that a rate assumption is required).

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