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

Annotations already declare it a read-only, closed-world operation, so the safety bar is low. The description then adds genuine behavioral context beyond that: the binary-search approach, the two ratio thresholds applied, the stress-test rate, the down-payment tier logic, and the insurability ceiling — none of which the annotations supply.

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, no filler: the first front-loads the purpose and the qualifying rules, the second lists the return values. It is dense but every clause earns its place; minor credit withheld only because the first sentence packs several distinct constraints into one long clause.

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?

With no output schema, the description correctly spells out the returns (max price, max mortgage, CMHC premium, monthly payment, GDS/TDS ratios), and annotations cover the safety profile. For a 12-parameter domain calculator this is nearly complete, though it does not tie the ratio rules back to the specific inputs that drive them.

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 coverage is 67%, so the schema carries most of the parameter meaning (units, defaults, ranges, enums). The description adds domain framing — down-payment tiers and the CMHC ceiling — but does not clarify individual parameter behavior (e.g. how downPaymentMode interacts with downPayment) beyond what the schema states. 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?

States a specific verb+resource ('work out the maximum home price a Canadian buyer qualifies for') and pins down the exact domain scope: GDS 39%, TDS 44%, OSFI stress-test, Dec-2024 down-payment tiers, $1.5M CMHC ceiling. This clearly separates it from siblings like mortgage_payment and minimum_down_payment, which compute payments or down payments rather than qualification.

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 conveys when the tool is applicable (a buyer evaluating affordability under Canadian rules) but never routes the agent against the obvious alternatives. It does not say how it differs from, or when to prefer it over, mortgage_payment or minimum_down_payment, despite the sibling list containing both.

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