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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, but the description adds substantial value: the full arithmetic ($6,000 per qualifying person, 6% reduction over $75,000/$150,000), the per-spouse application on joint returns, and provenance with a date for the figures. It stops short of describing the return shape (single amount vs. per-spouse breakdown), which matters since there is no output schema.

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?

Four sentences, front-loaded with the verb and statutory basis, then mechanics, edge cases, and provenance. Density is high but nearly every clause carries a distinct fact; the provenance sentence is justified because it dates the constants.

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 7-parameter, no-output-schema calculation tool, the description supplies the formula and the notable edge cases (MFS = $0, per-spouse reduction). The remaining gap is the output shape and how invalid combinations are handled, which the agent must discover by calling.

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?

With 100% schema coverage the baseline is 3, and the description earns an extra point by explaining the phase-out math tied to magi and filing_status, including that the reduction is applied per spouse rather than to the combined $12,000. It does not address the birth_date vs. *_age_65_or_older precedence, though the schema already documents that fallback.

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 bounded resource: the 2025-2028 enhanced senior deduction under P.L. 119-21 mirroring Schedule 1-A Part V. The scope markers (65+, $6,000 per person, phase-out) clearly separate it from siblings like calculate_tips_deduction and calculate_overtime_deduction.

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 eligibility conditions that determine use: age 65+ by Dec 31, tax years 2025-2028, and an explicit exclusion that married_filing_separately gets $0. It does not, however, name sibling tools or tell the agent where to route a taxpayer who fails the age test (e.g., explain_eligibility).

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