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

Annotations already declare this as a read-only, idempotent, closed-world calculation. The description adds real behavioral context beyond that: whole-dollar loan sizing, exact cents arithmetic cross-checked against the rounded payment, and the downstream effect of purchase_price/max_ltv_pct on the binding limit. It does not mention return fields, but no destructive or auth behavior needs disclosing.

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, front-loaded with the core purpose, no filler. The second sentence efficiently covers optional inputs and the arithmetic guarantee. Slightly dense but well-structured.

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 12-parameter calculation with no output schema, the description conveys the key outcome (largest whole-dollar loan, minimum down payment, which limit binds) and the rounding/arithmetic behavior. It does not enumerate the full return payload (e.g., resulting DSCR, payment split), but the annotations and schema carry most remaining weight.

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 100%, so the schema already documents all 12 parameters including defaults and bounds. The description restates the input set and highlights the default target DSCR but adds little syntax or meaning not already in the schema, and omits vacancy_pct and monthly_other_housing entirely. 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 precise verb (solves for) and a specific resource (largest whole-dollar loan at or above a target DSCR), with the exact constraints (PITIA, target default 1.25). This is clearly the inverse of calculate_dscr and rent_needed_for_target_dscr without ambiguity.

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 implies when to use it (finding the maximum loan size that holds DSCR) and explains the optional purchase_price/max_ltv_pct branch, but it never explicitly contrasts with calculate_dscr or the other siblings, nor states when not to use it. Usage is inferable rather than directed.

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