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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it is a safe, non-mutating calculation. The description adds valuable context beyond annotations by explaining that it marks which items are shoppable vs fixed by the county, and that it selectively applies FHA/VA/USDA fees. This provides useful behavioral nuance about the tool's logic without contradicting the annotations.

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?

The description is two sentences with no wasted words. The first sentence front-loads the core purpose and output, while the second adds two important behavioral details (shopping markers and loan-type fees). Every phrase earns its place, and the structure is easy to scan.

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?

The tool has 10 parameters, but the schema covers all of them with descriptions, so the description need not repeat parameter details. It explains the output (line items, total cash needed, shopping markers) and the loan-type fee logic, which is sufficient given the absence of an output schema. It does not address edge cases like VA fee exemptions, but defaults in the schema mitigate that gap.

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%, establishing a baseline of 3. The description adds meaning by tying cost categories (lender fees, title, appraisal, transfer taxes, prepaid escrow) to specific parameters like escrowMonths and transferTaxPercent, and by mentioning loan-type-specific fees that enrich the 'loanType' parameter. This contextual grouping helps the agent understand how inputs relate to the overall calculation.

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 clearly states it produces line-by-line buyer closing costs and total cash needed at the table, including the down payment. This distinguishes it from sibling tools that focus on monthly payments or single cost components. The verb 'Itemise' in the title is reinforced by the description's detailed enumeration of cost categories.

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 provides clear context by specifying the exact output (closing cost breakdown, total cash needed) and the types of costs included, implying when to use this tool. However, it does not explicitly name alternatives or state when not to use it, such as 'use calculate_mortgage for monthly payment estimates.' This is a minor gap given the many sibling calculation tools.

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