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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the description's main contribution is the boundary it sets: this is a hypothetical pure calculation with 'No bank offer, eligibility or savings recommendation.' It also clarifies that money is integer agorot and interest is a decimal, and specifies fixed-rate/unindexed nature—all behaviorally relevant details absent from the structured data.

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 concise sentences with zero filler. The main purpose is front-loaded, followed by necessary unit notation, and a boundary statement—each 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?

The tool has an output schema and comprehensive annotations, so the remaining gaps are small. The description supplies the purpose, the mathematical nature of the calculation, the unit conventions, and the limits of what the tool returns. A little more detail on term_months would push it to a 5, but it's adequate for safe 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?

Schema description coverage is 0%, so the description must compensate. It maps 'integer agorot' to principal_agorot and 'annual interest is a decimal' to nominal_annual_decimal, and the phrase 'fixed-rate unindexed annuity' explains how the parameters fit together. However, it doesn't explicitly discuss term_months, leaving that parameter to be inferred from its name.

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 uses a specific verb ('calculate') and names the resource ('hypothetical fixed-rate unindexed annuity'), making its function unmistakable. It also includes a clarifying boundary ('No bank offer, eligibility or savings recommendation') that helps distinguish it from potential real-world mortgage tools, though it doesn't explicitly name sibling tools.

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 useful context: the calculation is hypothetical and explicitly states it is neither a bank offer nor a recommendation, telling the user when not to rely on it. It doesn't explicitly mention alternatives like calculate_ltv_ratio or calculate_pti_ratio, but the sibling names are distinct and the context is clear enough to guide correct usage.

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