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

Annotations already declare readOnly, idempotent, closed-world, and non-destructive, so the safety profile is covered. The description adds genuinely valuable behavior beyond that: the authoritative source (IRS), the statutory basis (P.L. 119-21 sec. 70106), and an explicit warning that the 2026 figure is not the TCJA sunset, which directly guards against the most likely agent error.

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 field enumeration is front-loaded and the most decision-relevant correction (2026 is $15M, not the sunset) arrives early. The citation of specific dollar figures is somewhat dense but each figure serves as a verifiable anchor against stale model priors, so little is wasted.

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 one optional parameter and no output schema, the description does the work of listing every returned field, which is what an agent most needs. It does not clarify the response envelope (single record for the requested year versus a table across years), leaving a small gap in what to expect back.

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 description coverage is 100% and the single 'year' parameter is fully documented with range and default 2011-2026/default 2026. The description restates the range ('Years 2011-2026') but adds no new semantics such as out-of-range behavior or how partial-year data is handled, so the schema does the heavy lifting.

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 opens with a precise verb and a full enumeration of the values returned (basic exclusion amount, applicable credit, filing threshold, annual gift exclusion, non-citizen spouse exclusion, GST exemption, top rate), so an agent knows exactly what data it gets. It does not explicitly differentiate itself from the sibling tools calculate_estate_tax, check_gift, or compare_years, so it stops short of a 5.

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?

Usage is only implied: an agent must infer that this is the lookup tool for raw statutory figures versus the calculating/comparing siblings. The line 'Models trained before mid-2025 often predict the sunset' hints that this tool should be trusted over model memory, which is useful context but not an explicit when-to-use/when-not-to-use statement.

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