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

With no annotations, the description carries the full behavioral burden. It discloses the data source ('latest IRS brackets from CDN data'), the scope (federal and state), and the calculation outputs (bracket-by-bracket, marginal vs effective). It does not mention limitations (e.g., no AMT, US-resident only) or side effects, but for a calculation tool this is adequate. It adds context beyond the obvious 'calculates tax.'

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 with no wasted words. The main purpose is front-loaded ('US income tax for 2026'), followed by specific outputs and data source. Every word earns its place; it is concise and 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?

Given the 5 parameters and no output schema, the description should explain return values. It lists the key outputs (federal bracket-by-bracket, state tax, marginal vs effective rate), which gives an agent a clear idea of what the tool returns, though it does not specify the exact format (e.g., a single number vs an object). It also does not mention standard deduction handling, but the schema covers deduction parameters. For a calculator, this is reasonably complete.

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?

The input schema covers 100% of parameters with descriptions, so the baseline is 3. The tool description does not add meaning to any specific parameter beyond what the schema already provides; it mentions 'state tax' and 'marginal vs effective' which relate to state and grossIncome, but these are already explained. The description does not clarify parameter interactions (e.g., how preTaxDeductions affect federal brackets), so it adds no extra value.

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 clearly specifies a unique resource ('US income tax for 2026') and distinct functionality (federal bracket-by-bracket, state tax, marginal vs effective rate). It is easily distinguished from siblings like calculate_1099k_tax, calculate_capital_gains_tax, and calculate_freelancer_tax, which target specific income types. The inclusion of the year and data source adds precision.

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 it is for general US personal income tax, not for specialized forms like 1099-K, capital gains, or self-employment. However, it does not explicitly state when to use this tool versus alternatives, such as 'use for W-2 income' or 'not for self-employment.' It provides clear context (federal+state, 2026) but lacks explicit exclusions.

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