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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds beyond this by explicitly stating it does not change page/account state, does not access BetterOff customer data, and does not provide personalized financial advice. These are important behavioral boundaries not covered by annotations, and they complement the read-only nature without contradiction.

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?

The description is two sentences with no redundancy. The first sentence front-loads the purpose and core inputs; the second sentence clarifies behavioral limits and data access. Every phrase earns its place, and the structure is easy to scan quickly.

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 tool has 14 parameters all described in the schema, an output schema, and comprehensive annotations, the description adds the key contextual details: the 2026 tax year, educational nature, and the guarantee that it does not touch account data or give advice. This is sufficient for an agent to understand the tool's role and limitations, though it does not elaborate on edge cases or return format, which is acceptable given the output schema.

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 14 parameters. The description adds a high-level grouping of input types (salary/hourly, pay frequency, filing status, state, W-4, FICA, pre-tax deductions) that helps an agent understand which parameters belong together, but it does not add semantics beyond what the schema descriptions already provide. The baseline 3 for full schema coverage 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?

The description clearly states a specific verb (estimates) and resource (take-home pay for 2026), lists the input categories, and distinguishes itself from sibling calculators by naming the exact computation. It is not a tautology and immediately conveys what the tool does.

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 the tool is for paycheck take-home estimation but does not explicitly state when to use it over alternative calculators (e.g., calc_compound_interest, calc_retirement). It mentions 'educational' and 'without providing personalized financial advice,' which hints at scope boundaries, but it does not name alternatives or exclusion conditions. The context is clear but not explicit enough for agents picking among many siblings.

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