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

Annotations already declare a safe, idempotent, read-only, closed-world operation, so the bar is lower. The description goes beyond them by disclosing computational behavior (Social Security wages capped at 184500, additional Medicare tax applied, state rate applied flat to full salary) and by mandating that the calculator_url from the result be surfaced as a clickable markdown link — an output-handling obligation the annotations cannot express.

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, each with a distinct job: what is computed, when to use it plus the alternative, and the required output-link behavior. The scoping and routing information is front-loaded, and the parenthetical tax breakdown is dense but load-bearing rather than filler.

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?

With an output schema present, return values need no explanation, and the annotations carry the safety profile. The description still supplies everything an agent needs for correct invocation: the computation scope, the triggering intent, the sibling to route away to, and the post-call obligation to render calculator_url as a markdown link.

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%, with per-parameter descriptions covering salary, filing status enum, pay frequency, pretax deductions, and the state rate, so the baseline is 3. The description adds domain framing (which taxes the state rate and deductions interact with) but no per-parameter syntax or format detail beyond what the schema already provides.

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 computation and resource: per-paycheck net pay, enumerating the exact tax components (federal income tax, FICA with the Social Security wage cap and additional Medicare tax, flat state tax, pretax deductions). It explicitly distinguishes itself from the closest sibling by naming calculate_income_tax_estimator as the annual-picture alternative, so an agent can route without opening either 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?

"Use when the user wants take-home pay per paycheck after federal tax and FICA" gives an explicit triggering condition, and the following sentence names the alternative tool and the condition that selects it (annual tax picture). Both the when-to-use and the when-to-use-something-else are covered with no inference required.

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