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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses that the tool is 'Deterministic, idempotent calculation with zero external side effects' and warns that it 'uses ordinary floating-point arithmetic, keeps no dated table of official rates, and has not yet passed our full reference-test suite.' It also reveals the core formula and PE threshold behavior, providing meaningful context beyond structured data.

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 dense but organized into purpose, behavior, and usage paragraphs, with no filler. The only minor structural weakness is that the precision caveat appears before the main purpose statement, which slightly delays the agent's understanding of what the tool does.

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 tax calculator with zero required parameters, all inputs defaulted, and full schema descriptions, the description covers the computation formula, the PE threshold, the gross-up mechanism, and the recommended alternative tool. It does not explicitly describe the output structure, but the computed results—gross amount, treaty savings, and PE alert—are strongly implied.

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 baseline is 3; the description adds value on top by explaining how the parameters relate: 'Gross = Net / (1 - WHT_rate)' and by framing daysInCountry and treaty versus statutory rates in terms of PE alerts and treaty relief savings. It does not need to repeat every parameter's schema description.

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 names a precise verb and resource: 'Calculate cross-border B2B consulting/software invoice tax gross-up, statutory vs DTAA bilateral tax treaty withholding rates... and Permanent Establishment (183-day) tax audit exposure.' This clearly differentiates it from sibling tax tools, especially because it explicitly invokes feie_nomad_tracker as the alternative for a different use case.

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 'Usage Guidelines' paragraph is explicit and actionable: 'Use when exporting services cross-border or structuring international client contracts subject to foreign withholding tax. Do not use for digital nomad individual income tax exclusion; use feie_nomad_tracker instead.' This gives both a positive trigger and a named alternative.

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