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

Annotations cover readOnly, idempotent, and non-destructive hints, but the description adds crucial behavioral context: the tool is loan-side only, does not model tax cost of filing separately, and explicitly states that the answer acknowledges this limitation. It also clarifies that the output is a 'swing' comparison, which is more nuanced than a single payment figure.

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 with no wasted words. The primary function is front-loaded, and the key limitation is captured in a clearly separated, all-caps caveat. Every sentence earns its place.

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 read-only comparative tool with no output schema, the description adequately defines the output (swing in payment and lifetime cost) and the main limitation (tax cost excluded). The required parameters are fully covered by the schema. Minor unknowns remain, such as which specific IDR plans are considered, but these do not block correct invocation.

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?

The input schema already documents all 6 parameters with 100% coverage, including descriptions for balance, ratePct, loanType, spouseAgi, dependents, and borrowerAgi. The description does not add parameter-level detail, but it does frame the purpose (same federal loan book) that ties parameters together. Baseline 3 is appropriate.

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 states a specific action ('Run the same federal loan book filing jointly and filing separately') and a concrete output ('report the swing in the best income-driven plan's payment and lifetime cost'). This clearly differentiates the tool from siblings like compare_federal_student_loan_repayment_plans, which focuses on plan types rather than marital filing status.

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 gives clear context: it is for comparing married filing jointly vs separately for federal loans, focusing on income-driven plan outcomes. It does not explicitly name alternatives or provide exclusion criteria, but the 'LOAN SIDE ONLY' caveat implies when other tools might be needed (e.g., for tax-cost modeling).

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