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

Annotations already establish this as a safe, idempotent, non-destructive read, so the description correctly focuses on behavior: the $25,000 per-return cap applied identically across filing statuses, the $100-per-$1,000 MAGI phase-out above $150,000 ($300,000 joint), the self-employed net-income ceiling, and the zeroed-out MFS case. It also discloses provenance and vintage of the figures (irs.gov, Oct 2026), which matters for a statutory-formula calculator tied to a specific law.

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?

Front-loaded with the formula and cap before the phase-out and edge cases, and no sentence is filler. It is dense to the point of requiring a re-read on the nested parentheticals ($150,000 / $300,000 joint) and the final provenance sentence, though that sentence does add value.

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 6-parameter, output-schema-less calculation tool, the description supplies the full computation logic and the key edge cases. The remaining gap is the result surface — whether it returns just a deduction amount, a phase-out ratio, or also an eligibility note — plus behavior on disallowed filings.

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 baseline would be 3; the description earns above baseline by explaining how parameters interact rather than restating them — MAGI drives the phase-out at two different thresholds depending on filing status, and self_employed_tips are constrained by that business's net income. It does not, however, clarify what happens on an MFS input (return zero vs. error) or the ordering of cap-before-phase-out.

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 verb (calculates) and a precisely scoped resource (the 2025-2028 federal tips deduction under IRC 224 / Schedule 1-A Part II). The subject matter is clearly distinct from the sibling tools (overtime, senior, tax savings, eligibility), so an agent can route without opening 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?

Gives clear applicability context: valid tax years 2025-2028, an explicit exclusion (married filing separately gets $0), and the self-employed net-income limitation. What it lacks is any routing language toward siblings such as explain_eligibility or estimate_tax_savings when the agent needs eligibility reasoning rather than a number.

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