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

Beyond the readOnlyHint and openWorldHint annotations, the description reveals the simulation method (30-year deterministic plus 500-scenario Monte Carlo), the returned decision metrics, and the data-source behavior when address is provided. It also flags a realistic failure mode with monthly_rent, giving the agent useful trust-calibration context.

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 dense but not wasteful: a short question and method summary up front, followed by two high-value caveats and an explicit precedence rule. Every sentence contributes to correct tool selection or invocation, and the structure front-loads the core question.

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?

Given 10 parameters and no output schema, the description covers the decision type, method, main outputs, the most common input misunderstanding, and address-related behavior. It does not specify output units/conventions such as whether probability is a 0–1 fraction or percentage, but the defaults and parameter names fill most remaining gaps.

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 carry the parameter-semantics burden. It does this well for the most critical parameter, monthly_rent, explaining that it is rent for the same home, not landlord income, and adds caution about its relationship to home_price. It also clarifies address's effect and precedence, though the other eight parameters are left to their titles and defaults.

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 the exact decision being modeled, then names the engine and the concrete outputs (probability buying wins, breakeven hold period, net-worth outcomes). It also disambiguates the owner-occupant buy-vs-rent case from landlord rental cash flow, making the tool's purpose unambiguous and distinct from the sibling real-estate 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?

It gives clear operational guidance: monthly_rent must be the rent for the same home, this is not a landlord cash-flow model, and a rent far out of line with home_price should be confirmed before trusting the verdict. It also explains when address-based ZIP data is used and that explicit parameters take precedence. It does not explicitly route among sibling tools, which keeps it from a 5.

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