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

With no annotations, the description carries the full burden. It usefully discloses the tax regime behavior (US bracket-based vs flat rate elsewhere) and the default output shape (compact summary with 5-year milestones vs full array). However, it omits significant behavioral traits for a 28-param simulation model — notably whether portfolio_volatility introduces stochastic/Monte Carlo paths or a single deterministic run, and whether the computation is expensive or long-running.

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 sentences, front-loaded with the verb and scope, then modeling domains, then return behavior. Dense but nearly every phrase carries information. Slight over-listing of modeled domains ('mortgage amortization, optional property sale') where a grouping would read tighter.

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 28-parameter tool with no annotations and no output schema, the description covers the return format and tax behavior but leaves large gaps: no explanation of how volatility changes results, no units guidance, and it claims to model 'pensions' while the schema exposes no pension parameter. Adequate but not complete 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 coverage is 57%, so the description must partially compensate. It adds real meaning for region (tax model selection), yearly_detail (return shape), and the growth→income switch/property-sale modeling themes, but the majority of the 28 parameters (partner survivor factors, mortgage/property amounts, household_type, currency) get no explanatory support in either place. Marginal value over 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?

The description opens with a specific verb+resource: 'Run RetireCrunch's full year-by-year Wealth Plan projection for a household,' and enumerates the modeled domains (income, pensions, expenses, portfolio growth, phase switch, mortgage, property sale, tax). This distinguishes it from the narrower FIRE siblings (calculate_fire_target, calculate_coast_fire) as the comprehensive projection engine.

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?

Usage is implied by 'full year-by-year Wealth Plan projection' and the yearly_detail toggle, but the description never states when to choose this over calculate_fire_target or calculate_coast_fire, nor any prerequisites or exclusions. An agent must infer the routing from the sibling names alone.

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