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

Annotations already declare a safe read-only, closed-world operation, so the bar is lower, and the description still adds real behavioral context: the GDS 39% / TDS 44% qualification constraints, use of the OSFI qualifying rate, and the fact that property tax and heating are estimated rather than supplied. It does not disclose the response shape or whether results are advisory only, which keeps it below a 5.

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 compact sentences with no filler, front-loaded with the primary output (max mortgage and home price) before the mode breakdown. The telegraphic style is dense but readable; minor polish would earn a 5.

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 an 8-parameter calculation tool with no output schema, the description covers the returned quantities, the two calculation paths, the regulatory ratio caps, and the estimated inputs. It does not explain how annualInterestRatePct interacts with the OSFI qualifying rate, which is the one substantive gap for this complexity.

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%, so the schema already documents every parameter including the mode enum and the income-vs-budget parameter split. The description reinforces which parameters belong to which mode, which is mild added meaning, but adds no format, unit, or default detail beyond the schema.

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 outcome (maximum mortgage and home price at the OSFI qualifying rate) and splits it into two clearly named modes, income vs. budget. It stops short of distinguishing itself from close siblings such as mortgage_affordability, mortgage_stress_test, or debt_service_ratio, so an agent cannot fully disambiguate from the name and description alone.

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?

Explicit conditional guidance exists for the two modes: mode='income' when you have income, debts and down payment; mode='budget' when you start from an affordable monthly payment. What is missing is when NOT to use this tool versus the many overlapping siblings (affordability, stress test, debt service ratio).

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