generate_tax_plan

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

The description adds meaningful behavioral context beyond the readOnly and idempotent annotations: the computation is deterministic, executed locally/privacy-first, and the output includes assumptions, source provenance, calculation trace, and explicit unsupported boundaries. This materially helps an agent trust and interpret the result.

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?

One dense sentence with no filler; every element—deterministic, privacy-first, structured results, assumptions, provenance, trace, unsupported boundaries—earns its place and conveys a distinct attribute of the tool.

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?

The tool is complex: 9 parameters, nested income objects, four filing-status enums, and tax-year constraints. The description focuses on output characteristics rather than invocation context, required fields, or input categories. The output schema covers return shape, but the description leaves too much for an agent to infer about how to call this tool correctly.

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 only 22%, yet the description names no parameters and gives no hints about taxYear, filingStatus, income, family, business, payments, education, stateCode, or deductions. It does nothing to compensate for the low schema coverage, so parameter semantics are effectively absent.

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 uses a specific verb ('Generate') and a specific resource ('tax plan'), then distinguishes the tool through traits like 'deterministic', 'privacy-first local', 'source provenance', and 'calculation trace'. These traits separate it from sibling tools such as generate_full_tax_report or simulate_tax_scenario without needing to open the schema.

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?

There is no guidance on when to use this tool versus alternatives like simulate_tax_scenario, generate_full_tax_report, or plan_multi_year_taxes. No exclusions, prerequisites, or decision conditions are given; usage context is only implied by the tool's name and the word 'plan'.

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